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 commands/rishi4792/compass/statusgit clone --depth 1 https://github.com/Rishi4792/compassWhat 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 | $0.00037 | $0.00580 |
| Opus 5 | $0.00018 | $0.00290 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
status 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 yesterday.
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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/compass:status
Print, at a glance, where the current Compass build is and what to do next — so a long build never leaves you wondering.
Orientation first (v0.28.0, INV-ORIENT)
Run compass.sh orient and show its output before anything else — the same renderer the other two front doors use, so all three show an identical, consistent picture instead of three hand-written variants that drift apart (INV-ONE-RENDERER). The UserPromptSubmit hook usually paints it before this command starts; run it explicitly if it did not.
Procedure
- Resolve the build (same identity rule as
/compass:resume): inside a build's worktree → that slug; elsecompass.sh active-builds(1 → it; >1 → list and ask which; 0 → "no active build"). Resolve state viacompass.sh state-root. - Run
compass.sh status "<state-root>/<slug>"— it readsprogress.md+plan.md+receipts.mdand prints: Status · Stage · Steps k/n · Last ✓ (last PASS receipt) · Next (the single next action + its exact command).- If
compass.sh active-buildsshows more than one in-flight build, ALSO runcompass.sh builds— the live table of every parallel build on this repo (slug · stage · branch · worktree). That's how you see what else is running before you act, and remember: if one merges, the others must passcompass.sh post-merge-check <slug>before they ship.
- If
- Print that block verbatim, then add one plain-English line on what the next action does. Do not recite the files.
Note
Read-only. If .claude/builds/ won't resolve, the user is not at the project root (where .claude/ lives) — say so and ask for the root.
v0.12.0 additions
Post-ship: round k/cap · consecutive-clean j/N · open PS m— rendered whenloop.logexists (the post-ship critique loop's live position; bounds parsed from the contract'spost-ship-loop:header).auto: SUSPENDED (driver)— rendered when.auto-suspendedexists (an interactive driver suspended the self-spawn viacompass.sh auto-suspend; budget metering stays armed;auto-resumere-arms).
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.
- yesterday First seen · 25 lines · 37 tokens per session scan A 4138e7fe8269
status is a command published in the GitHub repository Rishi4792/compass (2 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 580 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.