verify-pr

verify-pr is a command for coding agents from iampawan/Manifest. It costs 32 tokens per session (342 once invoked), scanned A, original, MIT.

A pull-request checker that compares code changes and test results with a feature contract's acceptance criteria—the conditions that define when the feature is done.

In plain words
What is it for?
Use it on a GitHub pull request to check Playwright tests and CI results, instrumentation calls, feature-flag gates, translations, and other required changes.
Why use it?
It shows which requirements are covered and highlights contract obligations missing from the code, before human review.

Command

Part of the manifest plugin — 28 skills, 15 commands shipped together

Install

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.

agentmods
npx agentmods add commands/iampawan/manifest/verify-pr
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

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.

agentmods badge for verify-pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/iampawan/manifest/verify-pr.svg)](https://agentmods.dev/commands/iampawan/manifest/verify-pr)
Your own site
<a href="https://agentmods.dev/commands/iampawan/manifest/verify-pr"><img src="https://agentmods.dev/badge/commands/iampawan/manifest/verify-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00342
Opus 5 $0.00016 $0.00171
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash d657d3344dbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-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 4d 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.

commands/verify-pr.md · 46 lines

What it actually says

/verify-pr

Lightweight PR verification — runs the verify-deployment skill in "static" mode (against the PR diff, not a deployed URL).

Usage

/verify-pr 123
/verify-pr https://github.com/<org>/<repo>/pull/123

What it does

  1. Fetches the PR via GitHub MCP.
  2. Reads the contract ID from the PR title or body (formats: [SC-005], Closes #issue-with-contract, or branch name prefix).
  3. Loads the contract revision.
  4. For each AC, checks:
    • Is there a Playwright test referencing this AC?
    • Did the test pass in the latest CI run?
  5. Looks for things the contract requires but the diff doesn't add:
    • Instrumentation events not fired in code
    • Feature flag gate missing
    • i18n strings hardcoded
  6. Posts a review comment with the coverage table and any gaps.

When to use

  • After the Implementer finishes, before human review.
  • Re-runs automatically on every push to the PR (via pr-verify.yml).
  • Manually invokable if you want to re-check a stalled PR.

Output

A PR review comment with:

  • ✅/❌ per AC
  • Missing instrumentation calls
  • Missing feature flag gates
  • Quality nits (TODOs, console.logs, etc.)
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.

  1. 4d ago First seen · 46 lines · 32 tokens per session scan A d657d3344dbe

Subscribe to this mod's changes

verify-pr is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 342 once invoked, about $0.0002 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.