A command-line skill for setting up and maintaining agent-compass, a project system for managing coding-agent skills. It can initialise a project, synchronise skills, check for drift and inspect development usage.

Use it to initialise compass, sync or migrate skills, run health checks, inspect the local development environment, and promote a project skill into compass.

It gives projects a consistent way to install and update their agent instructions without manually copying files. Checks and diagnostics help reveal setup problems or changes that are out of sync.

compass — Skill for Claude Code by me-cedric/agent-compass

Install

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.

Any agent

npx skills add me-cedric/agent-compass --skill compass

Clone the repo

git clone --depth 1 https://github.com/me-cedric/agent-compass

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/me-cedric/agent-compass/compass/github.svg)](https://agentmods.dev/skills/me-cedric/agent-compass/compass)

Your own site

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/compass"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/compass/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/compass"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/compass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,060 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00048	$0.01060
Opus 5.5	$0.00019	$0.00424
Sonnet 5.5	$0.00010	$0.00212
Haiku 4.5	$0.00005	$0.00106

Measured 10d ago against content hash a3ea9eb7e022, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compass 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.

skills/compass/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compass

Run ac from the project root. It never prompts. Exit 0 is success. Exit 1 is an error or drift. Exit 2 is a usage error. Every command takes --dry (show the changes, write nothing) and --json.

Commands that exist: ac init, ac sync, ac sync --to <tag>, ac check --frozen, ac doctor --tokens. Dev-loop commands: ac env, ac dev and ac run. The skills env, local-run and e2e tell how to use them. ac ui opens the local web UI: assets on and off, the recommended set for the stack, env, run, tests, usage, delivery, promote. ac usage shows tokens and cost by day, project and model. ac promote <skill> copies a project skill into compass. Compass owns the text between its markers and the files that ac sync lists. Put project rules outside the markers.

init

Confirm that the project is a git repository.
Run ac init --dry --json. Read the plan.
Run ac init. It creates .agents/compass.json and then syncs.
Run ac doctor. Fix each fail line. Report each warn line.
Run ac check --frozen. It must pass.
Report the changed files and the command results.

A project that has specs starts with spec-flow, section "Init from specs".

update

Run ac sync --dry --json. Read each change.
Run ac sync. To move to another compass version, run ac sync --to <tag>.
An item with the action kept is a file that the project edited. Compass keeps the edit.
To take the update for a kept item, revert the file. To stop updates for it, add its path to exclude in .agents/compass.json.
Run ac check --frozen. Then run ac doctor --tokens.
Do not edit a managed file to change compass behavior. Change compass, or add the path to exclude.

migrate

Use this for an old install: a submodule, a vendored copy, .agent/agent-compass.lock, or double skill copies.

Run ac migrate --dry.
If ac prints "migrate needs --docs", stop. Tell the user that this compass version migrates only the docs layout. For the docs, use spec-flow.
Show the plan to the user. Run ac migrate only after a yes.
Run ac check --frozen. Report each file that the command kept because the project edited it.

Read the full file on GitHub · 77 lines

Changes

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 First seen · 77 lines · 48 tokens per session scan A a3ea9eb7e022

Subscribe to this mod's changes

compass is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,060 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 2026-10-18.

Building agents DevOps and cloud agent-skills agentic-ai ai ai-agents automation claude

worker-integration

Worker-Agent integration for intelligent task dispatch and performance tracking.

ruvnet/ruflo · 14 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

compass

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

compass

init

update

migrate

What this file has done since we first saw it

Other skills, from other repositories

worker-integration

agentmail

foundry-config-setup

jetson-diagnostic

nemo-automodel-launcher-config

mochi-remind