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/spec)<a href="https://agentmods.dev/commands/dshakes/compass/spec"><img src="https://agentmods.dev/badge/commands/dshakes/compass/spec/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/spec"><img src="https://agentmods.dev/badge/commands/dshakes/compass/spec.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 | $0.00044 | $0.00661 |
| Opus 5.5 | $0.00018 | $0.00264 |
| Sonnet 5.5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
spec 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft a spec / intent for: ${ARGUMENTS:-the task we're about to do}.
The point: give the loop a ground truth. Tests prove the code works; the spec proves it does what was asked. The Builder implements against it; the Reviewer and QA verify against its acceptance criteria. Keep it short and honest — a spec that rots is worse than none.
Do
- Read the relevant code,
CLAUDE.md, and any linked issue first (don't spec in a vacuum). - Write
specs/<kebab-slug>.mdwith exactly these sections, tight:- Intent — 1–3 sentences: what outcome, for whom, why now.
- Acceptance criteria — a numbered, verifiable checklist (each item testable; prefer "given/when/then" where it helps). This is the contract.
- Non-goals — what this explicitly does NOT do (prevents scope creep).
- Constraints / invariants — perf, security/tenancy, back-compat, dependencies.
- Verification plan — how each acceptance criterion will be checked (test, manual, metric).
- Open questions — anything needing a human decision before/while building.
- If a load-bearing invariant changes, say "needs ADR" and stop short (use
/adr). - Keep it under ~1 page. Commit it (
git add specs/… && git commit). Report the path.
Then (spec-driven loop)
Hand the spec to implementation: ~/compass/sdlc/orchestrate.sh "<task>" with
SDLC_SPEC=specs/<slug>.md set — the Planner plans to the spec, the Builder implements it,
and the Reviewer is told to verify the diff against the acceptance criteria (flag any
unmet or out-of-scope). The human approves the spec (intent), not just the diff.
End to end (cloud loop too): commit the spec in the same PR (it lives under specs/),
or add a Spec: specs/<slug>.md line to the PR description. The GitHub Reviewer
(sdlc-review.yml) detects the spec, verifies the diff against its Acceptance Criteria, and
marks unmet criteria or out-of-scope changes as Blocking — so the auto-fix loop converges on
intent, not just "tests pass." Same human merge gate.
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 · 40 lines · 44 tokens per session scan A a603ce512696
spec is a command published in the GitHub repository dshakes/compass (20 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 661 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).