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/dshakes/compassWrote 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/dshakes/compass/pr)<a href="https://agentmods.dev/commands/dshakes/compass/pr"><img src="https://agentmods.dev/badge/commands/dshakes/compass/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.
<a href="https://agentmods.dev/commands/dshakes/compass/pr"><img src="https://agentmods.dev/badge/commands/dshakes/compass/pr.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 | $0.00011 | $0.00264 |
| Opus 5.5 | $0.00004 | $0.00106 |
| Sonnet 5.5 | $0.00002 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
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 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.
What it actually says
Prepare and open a PR for the current branch.
Branch: !git branch --show-current
Commits not on the base: !git log --oneline @{u}.. 2>/dev/null || git log --oneline -10
Diff stat: !git diff --stat $(git merge-base HEAD origin/main 2>/dev/null || echo HEAD~5)..HEAD
- If I'm on a protected branch (main/master), stop — I need a feature branch first.
- Draft a PR title (use $ARGUMENTS if given) and a body with: What changed and why, a short testing section (what you ran), and any risk/rollout notes. Match the repo's PR style if there's a template.
- Show me the title and body. On my confirmation, push the branch and run
gh pr createwith them. Never force-push.
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 · 18 lines · 11 tokens per session scan A 9f6623a73dca
pr is a command published in the GitHub repository dshakes/compass (19 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 264 once invoked, about $0.0000 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.
code-review
Run the code-reviewer subagent on the current diff against origin/development (review-only, no edits).
review-changes
Alias for /code-review kept for backwards compatibility with the existing /feature-pipeline workflow.
audit
Audit a window of recent commits for real defects, confirm each finding before fixing, verify every surface a fix touches, then report confirmed/dismissed/no-op with evidence. Enforces Law 4 (Verify Before Reporting).
gsd:inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
gsd:pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.