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/fatihguner/foreman/claude-mdgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/claude-md)<a href="https://agentmods.dev/instructions/fatihguner/foreman/claude-md"><img src="https://agentmods.dev/badge/instructions/fatihguner/foreman/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 5.1 | $0.05922 | $0.05922 |
| Opus 5 | $0.02961 | $0.02961 |
| Sonnet 5 | $0.01184 | $0.01184 |
| Haiku 4.5 | $0.00592 | $0.00592 |
Grade A, and why
foreman 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 6d 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 — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foreman — Project Context
Foreman is an open-source, AI-powered strategic advisor for entrepreneurs. It uses a layered architecture of Skills, Agents, Hooks, Memory, Diagnostics, Playbooks, Commands, and Output Templates to deliver contextual, framework-driven guidance. The project lives at foreman.sh and ships as a public GitHub repository.
Architecture Overview
Entrepreneur Input
|
├→ [Commands] — Structured input: /apply, /diagnose, /run, etc.
└→ [Hooks] — Natural language input: pattern matching → intent classification
|
[Orchestrator Agent] — Central brain, routes everything
|
├→ [Memory Agent].read() — Retrieve entrepreneur context (5-layer system)
|
├→ [Diagnostic Agent] — Triage: symptom → targeted questions → root cause
|
├→ [Skill Executor Agent] — Apply framework to entrepreneur's context
|
├→ [Playbook Runner Agent] — Run multi-step skill chains with checkpoints
|
├→ [Output Agent] — Format results for target audience
|
└→ [Memory Agent].write() — Persist results and decisions
System Layers
Core Content Layers
- Skills (
.claude/skills/) — 158 self-contained.mdfiles across 12 categories, each teaching one business framework, method, or practice. Every skill works standalone and can be invoked by an agent. Derived from 12 source collections. - Output Templates (
.claude/output-templates/) — 48 fill-in-the-blank professional documents across 5 audiences:investor/(10),board/(7),team/(13),self/(10),client/(8). - Diagnostics (
.claude/diagnostics/) — 20 triage systems (12 broad + 8 granular) that identify root causes through structured questioning. Each routes to specific skills, playbooks, and templates. - Playbooks (
.claude/playbooks/) — 20 multi-step recipes (12 core + 8 extended) that chain skills sequentially with checkpoints and decision points.
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.
- 6d ago First seen · 388 lines · 5,922 tokens per session scan A fe61fd73b10b
foreman CLAUDE.md is an instructions file published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 5,922 tokens to every session, about $0.0296 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
cc-thinking-skills CLAUDE.md
Instructions for tjboudreaux/cc-thinking-skills: Follow AGENTS.md for repository workflow.
project-legibility AGENTS.md
AGENTS.md instructions for perhapsspy/project-legibility, covering agents.md and 검증.
ai-plugin GEMINI.md
Gemini CLI instructions for PostHog/ai-plugin, covering posthog extension, available tool categories and guidelines.
quantcoder-plugin GEMINI.md
Gemini CLI instructions for nutdnuy/quantcoder-plugin: Follow AGENTS.md. Use skills/quantcoder-research/SKILL.md as the primary task guide for QuantCoder research-paper to QuantConnect workflows.
vectorworks-mcp-codex-plugin AGENTS.md
AGENTS.md instructions for BhaveshY/vectorworks-mcp-codex-plugin: This repository is the lightweight Codex companion for BhaveshY/vectorworks-mcp.
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.