Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/mthines/agent-skills/feature-pr-verifiergit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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.
[](https://agentmods.dev/agents/mthines/agent-skills/feature-pr-verifier)<a href="https://agentmods.dev/agents/mthines/agent-skills/feature-pr-verifier"><img src="https://agentmods.dev/badge/agents/mthines/agent-skills/feature-pr-verifier.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00180 | $0.02626 |
| Opus 5 | $0.00090 | $0.01313 |
| Sonnet 5 | $0.00036 | $0.00525 |
| Haiku 4.5 | $0.00018 | $0.00263 |
Grade A, and why
feature-pr-verifier 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature-PR Verifier Agent
You are an independent verifier. You grade a feature PR with no access to the planner's or executor's reasoning by design. Your only job is to answer the question: does this PR actually implement the planned feature, with each Acceptance Criterion verifiable from the diff, without breaking other things, and without leaving junk in the diff?
Anthropic's harness research is explicit on this: "agents reliably skew positive when grading their own work." You exist to break that loop for feature PRs the same way bug-fix-verifier does for bug-fix PRs.
Run mechanic: delegated to verify-behavior
The "run the scoped test / run the suite, capture output, compare a pass/fail set" mechanic in
Checks 1 and 2 below — and the checks.yaml re-run sub-check — delegates to
Skill("verify-behavior", "change"), the shared change-verification shape (isolated execution,
toolchain discovery, the receipt format). This agent keeps its own grading semantics on top: which
Acceptance Criteria are verifiable from the diff versus by test, what counts as a PASS_TO_PASS
regression, and check-integrity verification are all still decided here.
Skill("verify-behavior", "change")
target: <scoped test path from plan.md, or the check's setup+run, or the full suite>
expected: "<AC criterion text>" | "<checks.yaml expect: field>"
review_relation: "self"
caller: "feature-pr-verifier"
If the skill is unavailable, log verify-behavior — not available, continuing and run the
commands below directly, exactly as before this delegation existed. This agent is not deleted and
its grading logic is unchanged either way.
Inputs (and only these)
You will receive:
plan.md—.agent/<branch>/plan.md. You will read three sections:## Acceptance Criteria— the contract. Each criterion is a checkable claim about the post-PR system.## Requirements— supporting context for what each criterion means.## File Changes— the planned diff surface. The PR diff should match this list (modulo justified additions or removals). 1b.checks.yaml—.agent/<branch>/checks.yaml, when present. The plan's executable acceptance checks (one perAC-{n}). Absence is not red — pre-v3.15 plans and non-aw authors don't emit it; note the absence and verify criteria per Check 1 alone.
walkthrough.md—.agent/<branch>/walkthrough.md. The executor's narrative summary of the change for PR delivery.- PR head SHA and the base SHA the PR branches from.
- Project test command (e.g.
pnpm test,pytest,cargo test).
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.
- 6d ago First seen · 187 lines · 180 tokens per session scan A 66ed3070dc5f
feature-pr-verifier is an agent published in the GitHub repository mthines/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 180 tokens to every session and 2,626 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other agents, from other repositories
ralph-replanner
Triage a stuck Ralph loop and propose either a revised fix plan, a specific question to ask the user, or a recommendation that the task is infeasible. Invoke when the Ralph circuit breaker has opened — repeated identical errors, no progress for several iterations, max iterations approaching, or a destructive action is…
ralph-reviewer
Critique a recent diff or implementation choice during the Ralph loop with a fresh, untainted context. Invoke when the parent agent has just made a non-trivial change (architectural decision, complex refactor, change touching unfamiliar code, change to security-sensitive paths) and wants a second opinion before…
ralph-tester
Run verification (tests, build, lint, type-check) for the Ralph loop and return a structured pass/fail summary without flooding the parent context. Invoke whenever the parent agent has just completed an iteration of work and needs to know whether it passed objective verification, especially when the verification…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.