Report 011: Release drift, claude-opus-5, claude-opus-5-5

Type Release drift report

What moved Claude Opus 5.5 on release day, three skills

Models claude-opus-5 claude-opus-5-5

Headline Claude Opus 5.5 on the three skills and cases of Report 009, one case each, beside a fresh Claude Opus 5 arm on the same harness.

Receipts 6 receipts

Cite this

@techreport{driftproof-011,
  title  = {Report 011: Claude Opus 5.5 on release day, three skills},
  author = {Driftproof},
  year   = {2026},
  type   = {Release drift report},
  note   = {claude-opus-5, claude-opus-5-5},
  url    = {https://driftproofhq.com/reports/011/}
}

Report 011: Claude Opus 5.5 on release day, three skills

Release drift report. The first table is the type’s question: the model moves under the skill and the harness stays fixed. The second holds the model and moves the harness, which the type does not describe; the limits say how it is read.

Claude Opus 5.5 on the three skills and cases of Report 009, one case each, beside a fresh Claude Opus 5 arm on the same harness. Read by the runner’s own comparison of the with-skill arms, code-review-and-quality reads no separation detected, git-workflow-and-versioning reads no separation detected; not enough draws to conclude at this effect floor, documentation-and-adrs reads no separation detected; not enough draws to conclude at this effect floor. Separately, Claude Opus 5 re-run on the newer Claude Code against Report 009’s own receipts: code-review-and-quality reads no separation detected, git-workflow-and-versioning reads no separation detected, documentation-and-adrs reads no separation detected; not enough draws to conclude at this effect floor.

Every figure below is read from a receipt or a file published beside it, and each block names its files. The target model of the new arm is claude-opus-5-5, and every draw of every arm was judged by claude-opus-5.

Read from: docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/diff--model--code-review-and-quality.md; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/diff--model--git-workflow-and-versioning.md; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/diff--model--documentation-and-adrs.md; docs/reports/009/evidence/three-skill-comparison--driftproof--code-review-and-quality--receipts--code-review-and-quality-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/diff--harness--code-review-and-quality.md; docs/reports/009/evidence/three-skill-comparison--driftproof--git-workflow-and-versioning--receipts--git-workflow-and-versioning-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/diff--harness--git-workflow-and-versioning.md; docs/reports/009/evidence/three-skill-comparison--driftproof--documentation-and-adrs--receipts--documentation-and-adrs-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/diff--harness--documentation-and-adrs.md.

Limits, read these first

One case per skill. Each receipt carries a suite of 1, 1, 1 case, in the order code-review-and-quality, git-workflow-and-versioning, documentation-and-adrs, the cases Report 009 used. Nothing on this page describes how any of the three skills behaves on any other task, or how Claude Opus 5.5 behaves in general.
Few draws. Each arm drew between 3 and 10 generations, each judged 3 times, and each case’s band is the spread across its draws. With one case there is no spread across cases, and each receipt records its combined uncertainty on the lift as absent, single_case.
Not Report 009’s harness, for either arm. Report 009 ran on Claude Code 2.1.272. That version cannot call this model: an earlier start of this run stopped at its first call with the API’s answer version 2.1.280 or newer is required, and produced no receipt. Both arms of this run therefore used Claude Code 2.1.280, and each receipt’s sidecar records the version every one of its calls reported (see Run record). The first table holds that harness fixed and moves the model. It is not Report 009’s harness, so neither table puts a Claude Opus 5.5 figure beside a Report 009 figure.
The harness comparison moves more than Claude Code. The second table sets Report 009’s Claude Opus 5 receipts beside this run’s Claude Opus 5 receipts. Between them the Claude Code version changed, and so did the host: Report 009’s Claude Code binary was the darwin-arm64 build, and this run’s the linux-x64 build. So did the date, and every generation is a fresh draw. The runner, the judge, the grading template, the SKILL.md bytes, the cases, the draw rule and the caps are the same (see Setup). A separation in that table could not be put down to the Claude Code version alone.
The judge is one of the two models compared. Every draw in both tables was judged by claude-opus-5, Report 009’s judge, which is also the model of the older arm. This report does not measure whether that judge scores its own model’s text differently from another model’s. It is also not the judge the judge policy fixes for Driftproof’s reports, the departure Report 009 made, so these figures are comparable with Report 009 and not with Reports 001 to 008.
No reasoning effort was set. None of the 204 raw call records’ argv carries an effort setting, the guard adds none (guard.py), and no receipt records one (none recorded). Whatever each model’s default was on this surface applied. The tables read as the same surface with a different model, not as the same effort.
A verdict reads the with-skill arms only. The runner’s comparison of two receipts sets one receipt’s with-skill band against the other’s, per case. The baseline and lift columns are context: no verdict on this page is read from them, however far apart they are.
Verification levels. All six receipts of this run are TESTED, TESTED, TESTED, TESTED, TESTED, TESTED, each answered by a model the surface attested (answered_by.kind model, model, model, model, model, model).

What stayed fixed and what moved

The inputs are Report 009’s. The same SKILL.md bytes (skill.content_hash, the same in this run’s two receipts and Report 009’s for each skill: code-review-and-quality 13d360d7f786, git-workflow-and-versioning 91c8c72654ee, documentation-and-adrs b67a9f07ed10) and the same suites (suite.suite_hash: code-review-and-quality 5d729f885294, git-workflow-and-versioning 4e74150753d0, documentation-and-adrs 6cce54e7d9d0).

The runner is Report 009’s. Driftproof runner 0.10.1 on the claude-cli surface, with the flags Report 009’s run used: at most 80 calls and 8.00 dollars of estimated spend per skill run. It puts the SKILL.md text in the prompt for the with-skill arm and gives the baseline arm the task alone, with no tools in either. It draws generations per arm until the spread settles or a maximum is reached, and the judge scores each draw against the case’s rubric on a continuous 0 to 1 scale.

The judge is Report 009’s. claude-opus-5, with the grading template 82586d1e44f8 in all three.

The rule. A case’s band is its mean across draws plus or minus the sample standard deviation across draws: a descriptive spread with no coverage probability. Two with-skill bands separate under the rule when they do not overlap and their means differ by at least the 0.05 effect floor. A case that does not separate is read under spec 035’s rule: when the two arms’ spreads and draws could not have resolved a shift of the floor’s size, it reads not enough draws to conclude at this effect floor, and otherwise no separation detected. Neither is evidence that nothing differs. The verdicts are the runner’s: driftproof diff over each pair, whose outputs are published below.

Read from: docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.json; docs/reports/009/evidence/three-skill-comparison--driftproof--code-review-and-quality--receipts--code-review-and-quality-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json; docs/reports/009/evidence/three-skill-comparison--driftproof--git-workflow-and-versioning--receipts--git-workflow-and-versioning-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.json; docs/reports/009/evidence/three-skill-comparison--driftproof--documentation-and-adrs--receipts--documentation-and-adrs-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.stdout.txt; config.js.

The low figures, read before the verdicts

Three figures on this run read low, and a low figure can be an instrument defect rather than an answer: a truncated generation, a refusal, a tool error, a timeout or a judge reply that did not parse. Report 007’s timeout defect is the precedent. Each draw behind these three figures was read, in the receipt and in the raw call record, before any verdict was written. None is an artefact, and no cell is excluded. The review is published as run-20260923T062806Z--artefact-review-20260923.md.

Claude Opus 5.5 without the skill on git-workflow-and-versioning, 0.300. Draws that ended their turn, untruncated and measured: three of three. Every judge sample reads 0.3. Each draw is a complete commit message whose subject line begins Fix password-reset links with no conventional type prefix, and the rubric reads if the subject line does not use a conventional type prefix, cap at 0.3. The judge’s reason: Body strongly explains cause and user-facing impact, and subject is specific, but subject lacks the conventional `fix:` type prefix, triggering the 0.3 cap. A real answer, judged low.
Claude Opus 5.5 without the skill on code-review-and-quality, 0.680. Draws that ended their turn, untruncated and measured: four of four, with draw means 0.860, 0.483, 0.500, 0.877. The two low draws are complete reviews that label the leaked key and the logged customer data Critical and put the other findings under category headings, Correctness among them, with no severity label; the judge says so, for example are categories, not severity labels. A real answer, judged low, with the spread between draws.
Claude Opus 5.5 with the skill on documentation-and-adrs, 0.661. Draws that ended their turn, untruncated and measured: six of six, with draw means 0.483, 0.800, 0.600, 0.853, 0.697, 0.533. Each is a complete revised function. The low draws keep the expired-coupon TODO reworded rather than resolving or removing it, which the judge reads as a miss, for example left a reworded but still-bare TODO. A real answer, judged low.

One more draw, outside the three. In Claude Opus 5’s baseline on git-workflow-and-versioning, draw three of ten scored 0.00. The surface gives the model no tools, and the model wrote a Glob invocation out as text, followed by the words No files found., and gave no commit message. The judge scored that absence. It ended its turn, was not truncated, ran no tool and parsed, so it is the model’s own output and it is not excluded. It sits in a baseline arm, which no verdict here reads.

Read from: docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.json; driftproof-calls/041/stdout.jsonl (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS); driftproof-calls/042/prompt.txt (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS); docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.json; driftproof-calls/017/stdout.jsonl (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS); driftproof-calls/019/stdout.jsonl (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS); docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.json; driftproof-calls/056/stdout.jsonl (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS); docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json; driftproof-calls/133/stdout.jsonl (not published: a raw call record; its sha256 is in docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS).

The model: Claude Opus 5.5 against Claude Opus 5, both on this run’s harness

skill	Claude Opus 5, with skill, mean ± sd across draws	Claude Opus 5.5, with skill, mean ± sd across draws	with-skill delta	under the rule	baseline mean (Claude Opus 5; Claude Opus 5.5), context	lift (Claude Opus 5; Claude Opus 5.5), context
`code-review-and-quality`	0.901 ± 0.007 (3 draws)	0.910 ± 0.015 (3 draws)	+0.009	no separation detected	0.862; 0.680	+0.039; +0.230
`git-workflow-and-versioning`	0.861 ± 0.008 (3 draws)	0.838 ± 0.027 (3 draws)	-0.023	no separation detected; not enough draws to conclude at this effect floor	0.765; 0.300	+0.096; +0.538
`documentation-and-adrs`	0.804 ± 0.103 (7 draws)	0.661 ± 0.148 (6 draws)	-0.143	no separation detected; not enough draws to conclude at this effect floor	0.567; 0.567	+0.237; +0.094

The with-skill delta is the second with-skill mean minus the first. The rule column is the runner’s comparison of the two with-skill bands; the delta, the baseline means and the lifts are shown as context, and no verdict is read from them. A lift is a receipt’s with-skill mean minus its baseline mean.

The harness: Claude Opus 5 in Report 009 against Claude Opus 5 in this run

skill	Report 009, with skill, mean ± sd across draws	this run, with skill, mean ± sd across draws	with-skill delta	under the rule	baseline mean (Report 009; this run), context	lift (Report 009; this run), context
`code-review-and-quality`	0.918 ± 0.010 (3 draws)	0.901 ± 0.007 (3 draws)	-0.017	no separation detected	0.783; 0.862	+0.134; +0.039
`git-workflow-and-versioning`	0.862 ± 0.007 (3 draws)	0.861 ± 0.008 (3 draws)	-0.001	no separation detected	0.300; 0.765	+0.562; +0.096
`documentation-and-adrs`	0.822 ± 0.017 (3 draws)	0.804 ± 0.103 (7 draws)	-0.018	no separation detected; not enough draws to conclude at this effect floor	0.532; 0.567	+0.291; +0.237

The same columns, with Report 009’s receipt first. Report 009’s receipts are published with that report and linked here, not copied.

Read from: docs/reports/009/evidence/three-skill-comparison--driftproof--code-review-and-quality--receipts--code-review-and-quality-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/diff--harness--code-review-and-quality.md; docs/reports/009/evidence/three-skill-comparison--driftproof--git-workflow-and-versioning--receipts--git-workflow-and-versioning-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/diff--harness--git-workflow-and-versioning.md; docs/reports/009/evidence/three-skill-comparison--driftproof--documentation-and-adrs--receipts--documentation-and-adrs-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/diff--harness--documentation-and-adrs.md.

Three readings

1. Between the two models, the rule detects no separation on any of the three skills, and on two of them the draws could not have told. On code-review-and-quality the with-skill means differ by +0.009 and the rule reads no separation detected. On git-workflow-and-versioning they differ by -0.023; at these spreads the runner puts the draws that would have been needed at 16 per arm, against the 3 drawn. On documentation-and-adrs the move is the largest of the three, -0.143, and the two spreads sum to 0.251, which is at or above the floor, so no draw count at these spreads resolves it. None of this is evidence that the two models score these skills alike.

2. Claude Opus 5 on this run’s harness separates from its Report 009 receipts on no skill. The with-skill means move by -0.017 on code-review-and-quality, -0.001 on git-workflow-and-versioning, -0.018 on documentation-and-adrs. The rule reads no separation detected on the first two, and on documentation-and-adrs, where this run’s spread is 0.103 against Report 009’s 0.017, no separation detected; not enough draws to conclude at this effect floor. This is a statement about these draws on two harnesses and two hosts, not about Claude Code.

3. On two skills the two models’ baselines sit further apart than their with-skill scores, and no verdict here reads them. Without the skill, git-workflow-and-versioning reads 0.765 for Claude Opus 5 and 0.300 for Claude Opus 5.5, and code-review-and-quality 0.862 and 0.680. On those two skills the lifts therefore differ more than the with-skill scores do; on documentation-and-adrs the two baselines read 0.567 and 0.567. The runner’s comparison of two receipts does not read baseline arms, so this is offered as an observation to test on more cases, not as a finding; the section on the low figures says what those draws are.

Read from: docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/diff--model--code-review-and-quality.md; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.json; docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.json; docs/reports/009/evidence/three-skill-comparison--driftproof--code-review-and-quality--receipts--code-review-and-quality-claude-opus-5-2026-09-15.json; docs/reports/009/evidence/three-skill-comparison--driftproof--git-workflow-and-versioning--receipts--git-workflow-and-versioning-claude-opus-5-2026-09-15.json; docs/reports/009/evidence/three-skill-comparison--driftproof--documentation-and-adrs--receipts--documentation-and-adrs-claude-opus-5-2026-09-15.json; docs/reports/011/evidence/diff--harness--documentation-and-adrs.md.

Run record

The run. Run 20260923T062806Z, one skill at a time, the Claude Opus 5.5 arm first and then the Claude Opus 5 arm, code-review-and-quality first in each. The command file writes a status line after each skill run; there are six, each with exit status 0 and one receipt, the last at 2026-09-23T07:08:39Z. Each receipt’s run.date_utc is written by the runner and is not read here as a start or a finish.

The caps. Per skill run, the runner’s own caps, as in Report 009 (see Setup). Across the whole run, a guard in front of Claude Code allows 240 calls in all and 240 seconds per call. The run used 204 calls, and the six receipts record 0 unmeasured draws.

The harness. Claude Code 2.1.280, installed at the npm integrity the run record states, with runner 0.10.1 at Report 009’s integrity. The runner writes no Claude Code version into a receipt, and a receipt is sealed, so each receipt has a sidecar, <receipt>.surface.json, bound to it by its receipt_hash and recording the version each of its calls reported; the table gives it.

The price. The runner’s registry had no row for claude-opus-5-5, so this run used a copy of it with one row added, at 4 and 20 dollars per million input and output tokens, read from the vendor’s pricing page on the day of the run (docs-pricing-snapshot-2026-09-23.json). The row is this run’s only; the product’s registry does not carry it.

The cost. Metered spend was 0.00 dollars: the claude-cli surface runs on a subscription. The estimated API-equivalent below is every draw’s generation and judge token counts, as each receipt records them, at the prices each receipt froze, with cached input counted at the full input price, as the runner counts it.

arm	skill	calls	Claude Code reported by every call	generation, estimated USD	judge, estimated USD	total, estimated USD
`claude-opus-5-5`	`code-review-and-quality`	28	`2.1.280`	0.42	1.17	1.58
`claude-opus-5-5`	`git-workflow-and-versioning`	24	`2.1.280`	0.19	0.63	0.82
`claude-opus-5-5`	`documentation-and-adrs`	36	`2.1.280`	0.36	1.29	1.65
`claude-opus-5`	`code-review-and-quality`	24	`2.1.280`	0.67	0.96	1.63
`claude-opus-5`	`git-workflow-and-versioning`	52	`2.1.280`	0.87	1.49	2.36
`claude-opus-5`	`documentation-and-adrs`	40	`2.1.280`	0.75	1.43	2.17
all six				3.25	6.97	10.21

Integrity. Receipt hashes: claude-opus-5-5 code-review-and-quality 5c3ad19b40dd4b39, claude-opus-5-5 git-workflow-and-versioning ca69c3436d0dbfa5, claude-opus-5-5 documentation-and-adrs b924a435c70e0092, claude-opus-5 code-review-and-quality d7bd2fcd3dbea881, claude-opus-5 git-workflow-and-versioning 2ba4ef175d7f1caf, claude-opus-5 documentation-and-adrs 34107e18c90f3b20. Each validates with its receipt hash verified. The raw call records carry the SKILL.md text and stay unpublished; their sha256 are published.

Published evidence

The files this report makes public. The six receipts with their summaries, surface sidecars and the runner’s console output; the six driftproof diff outputs the verdicts are read from; the run record, its registry copy, the status lines, the review of the low figures and the sha256 of every raw call record; the pricing snapshot; and the call guard.

docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.json
sha256 07daeb3f464c09d33318bee34921a91b84c8b789ae0d1d4a2f0caa85a095b326
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.stdout.txt
sha256 b404b6011deb84f6a37eecaad3bede694c0f6b2120bc923d8fcfdba7e98a1bcc
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.summary.md
sha256 2e5e46216bd1147daf4d92d620a60b74d6d5ff85f1c6bc40675452e25228b9fd
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-2026-09-23.surface.json
sha256 bab7733ba5eb4c8d835d367134c513d0989670df856ce650c1061a0f6810bd7a
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.json
sha256 94f2eed19305f978ea87720e772ad71608e97c22407ed24ab6e6fe138deb571c
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.stdout.txt
sha256 2ab1f3ea0ccd5289914dacde01068559c984aadabe64cd5e5dccab429509a27f
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.summary.md
sha256 54f203b43249e2e1e524c0bacd2eb915276eaecbe3f42506a47a326084a00f52
docs/reports/011/evidence/code-review-and-quality-claude-opus-5-5-2026-09-23.surface.json
sha256 2b6b296ad44df26e452652b9e0e4dccecba795e348e90f5632fad2c9d962d57f
docs/reports/011/evidence/diff--harness--code-review-and-quality.md
sha256 a54d66a5e425ba0130d245ccebd96d7e7efa4e1f48778b1c279b72e3feebd449
docs/reports/011/evidence/diff--harness--documentation-and-adrs.md
sha256 fb066d689a11c3ecd7eb572b0ff0d132fa1e495d85a2984b0635e6bee20d20e4
docs/reports/011/evidence/diff--harness--git-workflow-and-versioning.md
sha256 f2d1dcab5e7c9ee64104953592949cd08c5f6dd9b63721b11e39f80b729d78f4
docs/reports/011/evidence/diff--model--code-review-and-quality.md
sha256 f0bfab5aaf5eac0b29415e08ad442aa09bd6ba58304a8cdb529d31c4220697b0
docs/reports/011/evidence/diff--model--documentation-and-adrs.md
sha256 0cb80c5630cbdcbd53bf6ea3142da6b8a96df8a7f3118d39ca203b3101b2b716
docs/reports/011/evidence/diff--model--git-workflow-and-versioning.md
sha256 f0f6b2e80948256e2c3481704d3c06fed986221cf08dd72b7286959634ab56ef
docs/reports/011/evidence/docs-pricing-snapshot-2026-09-23.json
sha256 c25bc98ae2d3d9406feaccbddc36755a345aa950e7efb1d96234f910bd19fb68
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.json
sha256 c0412b61639f45b2a5c5ac701eba977a6d643b9a6d91e6e86e3feaf45c9e4c86
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.stdout.txt
sha256 c2f80a9622330045e57275178688d15aa23c433f321420523f9f62d4c6321bff
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.summary.md
sha256 629287738812f9882da9154447e8ed9a365ce04e7ab0acbe6ec7abb4c9dfa4e2
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-2026-09-23.surface.json
sha256 a9322c335e39726f9ad7b76925add0d0cbd93b59465d818ab4de470797cfb7d2
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.json
sha256 61fe3ca86f3d41023169eea76653bac7b55318b2e1072c11bcb2a5247b6cccef
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.stdout.txt
sha256 590a76b48dfb0e3ce44cab9baf66225f6c7cbc3fd66ba8336c166f51643d6f93
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.summary.md
sha256 e680cc4da944011a219b2490237f43d6c0a17ab2e1d66c69ba5f11f8c8d08d0e
docs/reports/011/evidence/documentation-and-adrs-claude-opus-5-5-2026-09-23.surface.json
sha256 fd26d7a011c3a7b5de41d22ba34ccb5d792816048a89f3f5d14ad364a18b2c1e
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.json
sha256 27487953281201e3db25e32fdc8f868df132e2221bc01afc0e45e6f75a929c7d
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.stdout.txt
sha256 f54aac1969621e2946f1afcfecce2fb798681165f5bc8b9baf0e330bfe23c820
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.summary.md
sha256 757953a5b73384b27334c3c0e84b777f448d261369232e323446d4ba3fb0dcd7
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-2026-09-23.surface.json
sha256 1820211b222c21efcc04755a3cc1af5632d098874a971b75f59cbe7e35d7faa7
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.json
sha256 7cd9748196d1ef1abadc1314fb5b923b6b1fd9bb930eb3b986e27bb76193936b
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.stdout.txt
sha256 adefcff6997f9ebf11b19f470ed4c085cfcc94df5b6c77439001c2b661110286
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.summary.md
sha256 034ecb528ee8c1254ce862afa018374b68afe2d02c5d258a876205cdcae8cb24
docs/reports/011/evidence/git-workflow-and-versioning-claude-opus-5-5-2026-09-23.surface.json
sha256 6e1886d1a7493bbe1fdf53077bc7ea5bb2aa9099c833637829c1d6a730686f16
docs/reports/011/evidence/guard.py
sha256 4be011477676abe4c97a3234ce2462f064c0b3fd7611df2871892d547e420435
docs/reports/011/evidence/run-20260923T062806Z--artefact-review-20260923.md
sha256 f0d9fae004c11a5d344d15a828f60bd3b601138ebcd20e6183e3d6db85bea7bb
docs/reports/011/evidence/run-20260923T062806Z--driftproof-calls.SHA256SUMS
sha256 7397d5230f4881bd037b94a07571301d8f9afe86ba90911e9f3f2e2f2420cd65
docs/reports/011/evidence/run-20260923T062806Z--registry.json
sha256 2a0a6dd787d6a5f5255621e1eb48497eee30d31c470ed7be0c81366e08d252fd
docs/reports/011/evidence/run-20260923T062806Z--run-record.json
sha256 2696c287fd6115795c0fcbc4743a9be80872d5181a488bba60c33a20ad956b45
docs/reports/011/evidence/run-20260923T062806Z--status.jsonl
sha256 f4ba381a121115c0db26b37a85f29f9fc34c80e4fe3ac4d7cdd85722eec11bfd

Report 009’s three receipts, the other side of the second table, are published with that report: code-review-and-quality, git-workflow-and-versioning, documentation-and-adrs. Validate a receipt with npx driftproof validate <file>. Each copy here is byte-identical to its twin under specs/042-opus-5-5-release-receipts/, and each sidecar names the receipt it belongs to and that receipt’s hash.