A pull-request review procedure that checks a fixed commit—the exact version of the code under review—and writes a verifier report. It compares the changes with the main branch, runs the project's checks, and records what ran, what did not, and whether the result passes.

Use it to inspect an AgentDescent pull request, run its test and documentation checks, and produce a pass, fail, or inconclusive review report.

It replaces relying on the pull request description with independently checked evidence. Reviewing the exact commit also prevents the code from changing unnoticed during review.

How Birfy/agentdescent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Birfy/agentdescent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Birfy/agentdescent/main/.claude/skills/review-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Birfy/agentdescent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/birfy/agentdescent/review-pr/github.svg)](https://agentmods.dev/skills/birfy/agentdescent/review-pr)

Your own site

<a href="https://agentmods.dev/skills/birfy/agentdescent/review-pr"><img src="https://agentmods.dev/badge/skills/birfy/agentdescent/review-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/birfy/agentdescent/review-pr"><img src="https://agentmods.dev/badge/skills/birfy/agentdescent/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 838 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00838
Opus 5.5	$0.00018	$0.00335
Sonnet 5.5	$0.00009	$0.00168
Haiku 4.5	$0.00005	$0.00084

Measured 9d ago against content hash 62abaa0367d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/review-pr/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentDescent review-pr

Produces a Verifier report for Birfy/agentdescent. The report is evidence, not merge authority: what may happen after a PASS is AGENTS.md › Merge policy.

Establish the tip

Work in a fresh clone (git clone https://github.com/Birfy/agentdescent), check out the PR head (gh pr checkout <n>), record git rev-parse HEAD. If the head moves during the review, start over.
Read the rules from origin/main, not a stale copy: AGENTS.md, CODE_STANDARDS.md, LESSONS.md, and this file (git show origin/main:.claude/skills/review-pr/SKILL.md).
Inventory the diff against the merge base (git diff origin/main...HEAD --stat) and get the tier: python3 .github/scripts/risk_gate.py --pr <n>. The PR description is narrative, not evidence.

Re-run the gates yourself

pip install -e ".[dev,mcp]"
pytest -q                               # the whole suite, not only the new tests
python -m tools.gen_api_docs --check    # when agentdescent/__init__.py or a public signature changed
python -m tools.changelog_fragments check
mkdocs build --strict                   # when docs/ or mkdocs.yml changed (needs .[docs])

Fails on main: copy only the new/changed test files onto the merge base and run them; they must fail there and pass at the tip.
Ark real-model checks only when the change touches a model path and ARK_API_KEY is already in the environment; otherwise list them under Not run:.

Instant FAIL

A key, token or credential anywhere in the diff.
A network or model call reachable from pytest -q.
docs/api.md edited by hand or out of sync; CHANGELOG.md edited in a PR.
A claimed fix with no test that fails on main.
An unconditional @pytest.mark.skip / xfail hiding a failure.
A port that departs from its source's released code without saying so.

Verdicts

Verdict	Meaning
PASS	No actionable findings; every gate you list under `Ran:` was run by you at this tip and is green
FAIL	An actionable defect (correctness, a hard rule, a missing fail-on-main test, a dishonest claim)
INC	Incomplete: a material check not run, the tip moved, scope unclear. INC is not PASS

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 79 lines · 46 tokens per session scan A 62abaa0367d7

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository Birfy/agentdescent (201 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 838 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.

Code review Testing Unit testing agent-framework agents ai-agents asynchronous evolutionary-algorithms gradient-descent

python-testing

Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.

microsoft/agent-framework · 29 tokens

aqe-review-quality

Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate evaluation, security/performance/testability review, or checking whether a change has sufficient verification. Do not use when the user primarily asks to implement a…

proffesor-for-testing/agentic-qe · 64 tokens

developer

Engineering templates for review, testing, refactoring, architecture, releases, and incidents.

conectlens/lenserfight · 19 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

verify-dotnet-samples

How to build, run and verify the .NET sample projects in the Agent Framework repository. Use this when a user wants to verify that the samples still function as expected.

microsoft/agent-framework · 40 tokens

regex-tester

Validate, test, and debug regular expressions by executing them against sample inputs. Use when asked to build, verify, or explain a regex pattern.

microsoft/agent-framework · 33 tokens

agentdescent: Skill for Claude Code