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 skills add SathiaAI/adversarial-review --skill pr-text-checkgit clone --depth 1 https://github.com/SathiaAI/adversarial-reviewWrote 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/skills/sathiaai/adversarial-review/pr-text-check)<a href="https://agentmods.dev/skills/sathiaai/adversarial-review/pr-text-check"><img src="https://agentmods.dev/badge/skills/sathiaai/adversarial-review/pr-text-check/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.
<a href="https://agentmods.dev/skills/sathiaai/adversarial-review/pr-text-check"><img src="https://agentmods.dev/badge/skills/sathiaai/adversarial-review/pr-text-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.00611 |
| Opus 5.5 | $0.00016 | $0.00244 |
| Sonnet 5.5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
pr-text-check 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 1mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR text check
The prose around a change (its PR body, commit messages, and changelog entry) is part of the deliverable. It is read far more often than the diff, so it must be true to the diff.
Before opening or updating a PR, verify:
- The description matches the diff. Every claim in the PR body corresponds to an actual change; every non-trivial change is described. Read the final diff and reconcile it line by claim — do not describe what you intended, describe what shipped.
- The CHANGELOG is updated in the same PR. Add an entry under
## [Unreleased]for any user-visible change (this repo's DoD requires it). Do not hardcode counts that will drift (reviewer counts, "N scenarios") — those are a repeat bug; assert them from code instead. Thepyprojectversion and the newest released heading must agree (a test enforces it). - Docs shipped with the code. Enumerate every affected
SKILL.md,README*,references/*.md, anddocs/file, and check claim-by-claim that each reflects the behavior change in this PR, not a follow-up. A sensitive surface ships its committed threat model and its review verdict in the same PR. - Status is honest. Say what is done, what is deferred, and what is BLOCKED/unknown — never round a partial up to done, never a BLOCKED (e.g. a permission gap) up to a pass. Name residual risks explicitly; a documented residual is honest, a hidden one is a defect.
- No scope drift in the text. If the change grew beyond its story, the PR says so and the growth is split out or justified — the text never quietly redefines the scope.
- No secrets in the text. No tokens, keys, or credential values in the body, commits, or the changelog. Attribution/footers follow the repo's convention.
- Commit messages are self-contained. Subject in the imperative; body says why, not just what.
Push a keepable commit the same turn — but only where you have explicit authorization to push (a
non-negotiable in this repo; see
AGENTS.md); otherwise hand the commit to whoever merges.
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.
- 1mo ago First seen · 36 lines · 40 tokens per session scan A e003c12cab6e
pr-text-check is a skill published in the GitHub repository SathiaAI/adversarial-review (3 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 611 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 2026-09-13.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.