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 instructions/bikeread/promethos/claude-mdgit clone --depth 1 https://github.com/bikeread/promethosWrote 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/instructions/bikeread/promethos/claude-md)<a href="https://agentmods.dev/instructions/bikeread/promethos/claude-md"><img src="https://agentmods.dev/badge/instructions/bikeread/promethos/claude-md.svg" alt="Measured on agentmods" 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 | $0.00750 | $0.00750 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
promethos CLAUDE.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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
PromethOS is a skills-first framework for designing, governing, evaluating, and evolving agent systems. The repository ships reusable SKILL.md prompts — no compiled code, no servers, no runtime dependencies. It supports Claude Code, Codex, and Gemini CLI via thin platform-specific entrypoints.
Validation (the only "test" gate)
./scripts/validate-skills.sh # structural checks on all skills
python3 ./scripts/check-repo-docs.py # required files + broken link checks
Both must pass before any PR. There is no build step.
validate-skills.sh checks: exactly one SKILL.md per skill directory, required frontmatter (name, description), combined name + description length of 250 characters or less, required headings, no duplicate skill names, and presence of bootstrap reference files.
check-repo-docs.py checks: required repo files exist (README, CONTRIBUTING, AGENTS, LICENSE, SECURITY, CODE_OF_CONDUCT, platform install docs, issue templates, PR template) and all local Markdown links resolve.
Skill Taxonomy
PromethOS now uses task-first skill ids instead of public prefix groupings.
- Core entry:
route-agent-design,define-agent-requirements,set-agent-autonomy-boundaries,build-agent-evals,debug-agent-failures,verify-agent-readiness - Design deepening:
choose-agent-architecture,plan-agent-implementation,design-agent-context,design-agent-memory,design-agent-permissions,design-agent-tools,orchestrate-agent-subagents,trim-agent-scope - Maintainer layer:
evolve-skill-library,turn-postmortem-to-improvement
Skill File Contract
Every skills/<skill-name>/SKILL.md must have:
Frontmatter: name, description
Put trigger language in description; do not add a separate when_to_use
field. Keep name + description at 250 characters or less.
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.
- 5d ago First seen · 78 lines · 750 tokens per session scan A 4fd81d47c155
promethos CLAUDE.md is an instructions file published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 750 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).