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.
git clone --depth 1 https://github.com/costajohnt/oss-autopilotWrote 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/commands/costajohnt/oss-autopilot/pr-ready)<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/pr-ready"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/pr-ready/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/commands/costajohnt/oss-autopilot/pr-ready"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/pr-ready.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 | $0.00045 | $0.01634 |
| Opus 5.5 | $0.00018 | $0.00654 |
| Sonnet 5.5 | $0.00009 | $0.00327 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
pr-ready scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pr-ready
This command drives the mandatory pre-commit review loop that the project's CLAUDE.md describes. It does not push or open a PR — it tells you whether the branch is ready to.
What it does
For the diff currently uncommitted-and-staged or already on the local branch (whichever applies):
-
Verify branch hygiene — confirm we're not on
main, the working tree has work to evaluate, and main has been pulled recently. If the working tree is clean and the branch matches main, abort with "nothing to review".Upstream drift check (mandatory). Re-fetch the upstream default branch and detect any commits since this branch diverged that touch files in this branch's diff:
git fetch <remote> <default> 2>/dev/null mergeBase=$(git merge-base <remote>/<default> HEAD) touchedFiles=$(git diff --name-only "$mergeBase" HEAD) overlappingCommits=$(git log "$mergeBase..<remote>/<default>" --oneline -- $touchedFiles)If
$overlappingCommitsis non-empty, surface the list and recommend re-vetting the issue before declaring READY. The same fix may have already merged; the CONTRIBUTING-style "no other open PRs" check passes vacuously when the duplicate has merged, so this drift check is the only safety net. Report as a Critical finding if any overlapping commits are found and the user hasn't acknowledged them. -
Run the project's lint+format checks:
pnpm run lintpnpm run format:check(if the project'spackage.jsondefines it)- Surface any failures inline; do not auto-fix unless the user explicitly asks.
-
Run the full test suite:
pnpm test. Block readiness on any failure. -
Dispatch the pr-review-toolkit agents in parallel against the diff:
pr-review-toolkit:code-reviewer— bugs, dead code, consistencypr-review-toolkit:silent-failure-hunter— error handling gapspr-review-toolkit:code-simplifier— refactoring opportunities
For larger PRs (>15 files or new logic with branches), additionally run:
pr-review-toolkit:pr-test-analyzer— coverage gapspr-review-toolkit:comment-analyzer— outdated/over-explanatory commentspr-review-toolkit:type-design-analyzer— when new types are introduced
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.
- 10d ago Changed · +3 lines da9a87f9bcb8
- 1mo ago First seen · 106 lines · 45 tokens per session scan A e3ae930819c6
pr-ready is a command published in the GitHub repository costajohnt/oss-autopilot (23 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,634 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 2026-08-30.
Other commands, from other repositories
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
implement-revalidate
Read by /implement when the user asks to re-validate (D-CMD-REF-HAND).
release-flow
Portable gated release flow — deterministic gate + vendor-agnostic independent reviewer, runnable from any harness.
code-review
Review the current branch changes for bugs and style issues.
create-pr
Create a pull request with proper template discovery and population.
address-pr-feedback
Systematically address PR review comments. Fetches all threads, categorizes by status (acknowledged, silently fixed, unaddressed), and guides user through posting replies and implementing fixes with explicit approval.