agentmods.dev

SkillCompass AGENTS.md

A repository-local guide that tells coding agents how to work in the project, including naming, language, commit, and source-of-truth rules.

In plain words
What is it for?
Use it when an agent creates branches, commits code, edits instructions, adds translations, or fetches test fixtures.
Why use it?
It keeps agent changes consistent with the project's required workflow and prevents rules from being missed.

Instructions file for CodexOpenCode

215 +1 4mo ago A scan 328 tokens original MIT
View the source file Evol-ai/SkillCompass
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.

agentmods
npx agentmods add instructions/evol-ai/skillcompass/agents-md
Clone the repo
git clone --depth 1 https://github.com/Evol-ai/SkillCompass

Made for: Codex, OpenCode.

Per session 328 This file is loaded in full into every session.
When invoked 328 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00328 $0.00328
Opus 5 $0.00164 $0.00164
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 2d ago against content hash 46e1ef45b229, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SkillCompass AGENTS.md 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 2d 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.

AGENTS.md · 19 lines

What it actually says

Agent Instructions

This file exists so agentic tools have a repository-local instruction entry point. For the full contributor guide, workflow, and repo structure, read CONTRIBUTING.md.

Required Rules

  • Branch names: ASCII only, kebab-case (e.g., fix/d5-delta-override, feat/d6-rubric-band). No spaces, no non-Latin characters.
  • PR titles: ASCII only. Keep under 70 characters. Use the description/body for details.
  • Commit messages: ASCII only. Follow conventional commit format (fix:, feat:, docs:, refactor:, chore:).
  • Code and technical files (.js, .ts, .json, .yml, schemas): English only. No non-English comments, identifiers, or string literals.
  • User-facing templates in SKILL.md and commands/*.md: English only at rest. Claude detects the user's locale at runtime and translates at display time per SKILL.md's Global UX Rules.
  • Runtime i18n resources (oc/src/locale.ts): the one place localized message catalogs live. Add new locales here.
  • Test fixtures: stored in a separate repo. Fetch with npm run fetch-fixtures. May contain any language.

Source of Truth

Keep this file aligned with the "Naming & Language Conventions" section in CONTRIBUTING.md.

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.

  1. 2d ago First seen · 19 lines · 328 tokens per session scan A 46e1ef45b229

Subscribe to this mod's changes

SkillCompass AGENTS.md is an instructions file published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 4mo ago), licensed MIT. It adds 328 tokens to every session, about $0.0016 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 2026-08-30.

Git and workflowLocalizationTestingagent-skillsanthropicclaude-codeclaude-code-skillopenclawskill-rating
Related

Other instructions, from other repositories

claude-blog CLAUDE.md

Instructions for AgriciDaniel/claude-blog, covering claude blog - blog creation & optimization skill, project overview, architecture, commands and development rules.

AgriciDaniel/claude-blog · 2,915 tokens

oh-my-mermaid CLAUDE.md

Instructions for oh-my-mermaid/oh-my-mermaid, covering project rules, readme localization, versioning, commits and terminology.

oh-my-mermaid/oh-my-mermaid · 311 tokens

thinking-toolkit AGENTS.md

Instructions for ponomr/thinking-toolkit, covering thinking toolkit — standalone context, critical rules, architecture, development commands and validation invariants.

ponomr/thinking-toolkit · 650 tokens

skills CLAUDE.md

Instructions for heygen-com/skills, covering claude.md — heygen skills, what this is, architecture, the 300-line rule and shared state.

heygen-com/skills · 2,095 tokens

ClawFleet CLAUDE.md

Instructions for clawfleet/ClawFleet, covering claude.md, project, architecture layers, clawsandbox (infrastructure) and clawfleet (product).

clawfleet/ClawFleet · 3,755 tokens

product-playbook CLAUDE.md

Instructions for Kaminoikari/product-playbook: Claude Code plugin: 16 product-planning lenses + a dev-discipline layer (six gates, dual reviewers, deterministic hooks).

Kaminoikari/product-playbook · 196 tokens