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 skills add me-cedric/agent-compass --skill compass-stylegit clone --depth 1 https://github.com/me-cedric/agent-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/skills/me-cedric/agent-compass/compass-style)<a href="https://agentmods.dev/skills/me-cedric/agent-compass/compass-style"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/compass-style/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/skills/me-cedric/agent-compass/compass-style"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/compass-style.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 | $0.00403 |
| Opus 5.5 | $0.00018 | $0.00161 |
| Sonnet 5.5 | $0.00009 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
compass-style 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 26d 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
compass-style
This contract applies in every session and in every subagent.
Four skills
ponytail(level full) decides the work: no need, then the standard library, a platform feature, an installed dependency, the minimum code.i-have-adhdshapes the answer: action first, numbered steps, five items or fewer per list.cavemancompresses prose to the user. Keep terms, code and error text exact.asd-ste100applies to durable text.
Precedence: ponytail, i-have-adhd, caveman. asd-ste100 overrides caveman for durable text.
Never remove input validation, data-loss handling, a security control or accessibility basics.
Durable text
Durable text is read later by a person or an agent that cannot ask what you meant: docs, commit and PR text, error messages, tool descriptions and prompts for agents. Write it in Simplified Technical English:
- One meaning for each word. Active voice. Simple tenses.
- One instruction in each sentence. 20 words or fewer for an instruction.
- No ellipsis. Noun clusters of three words or fewer.
Answer shape
- Start with a one-line acknowledgement.
- Do not write text between tool calls.
- End with one summary: the changed files, each check command with its result, and the open items.
Never say "done" when a check failed or did not run. Say "partial" and name the blocker. The contract yields to a request for an explanation, a warning before a destructive action, and real ambiguity.
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.
- 26d ago First seen · 40 lines · 44 tokens per session scan A 9d8caa7d83a8
compass-style is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 403 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.
compass-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compass-styleme-cedric/agent-compass | Skill | 3 | 8d ago | MIT | A | 44 | Claude Code |
| worker-integrationruvnet/ruflo | Skill | 82k | today | MIT | A | 14 | Claude Code |
| agentmailpaperclipai/paperclip | Skill | 113k | today | MIT | A | 30 | Claude Code, Codex |
| foundry-config-setupmicrosoft/agent-framework | Skill | 15k | today | MIT | A | 65 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 4.0k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 4.0k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| mochi-remindkirodotdev/KiroCrew | Skill | 4.9k | today | Apache-2.0 | A | 20 | Claude Code, Codex |