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/kouroshez/coding-os/agents-mdgit clone --depth 1 https://github.com/kouroshez/coding-osWhat 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 | $0.04587 | $0.04587 |
| Opus 5 | $0.02294 | $0.02294 |
| Sonnet 5 | $0.00917 | $0.00917 |
| Haiku 4.5 | $0.00459 | $0.00459 |
Grade A, and why
coding-os 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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS — Coding OS Development Protocol (META PROJECT)
Root entry point for agents working ON coding-os itself. Read first; re-read after context loss. Hard limit: keep this file under 120 lines — overflow goes to docs/. Architecture deep-dive: docs/architecture/meta-project.md.
Nature — Meta-Project
This repo IS the mother. Its output is projects shaped like itself: cos init composes three concentric layers (DNA → mRNA → phenotype) into a consumer project, and this repo is itself an instance of what it produces (P5 Dogfood; root CLAUDE.md symlinks to AGENTS.md).
src/core/— agent-agnostic, stack-agnostic kernel: hooks, MCP server, rules, skills. Cognitive layers on one MCP server (server.py): thinking_os (memory/learning/metrics) · graph_os (knowledge graph) · board_os (Scrumban).src/adapters/<agent>/— per-agent translation: how the kernel surfaces as.claude//.codex/.src/templates/<stack>/— per-stack overlay: skills + scaffold for one language/framework.
Modularity Map — Blast Radius
| Edit | Propagates to | Rebuild |
|---|---|---|
src/core/hooks/*.sh |
ALL consumer projects (live symlinks) | none |
src/core/thinking_os/** |
ALL projects pointing to this MCP | restart MCP client |
src/core/rules/*.md, src/core/skills/** |
ALL projects | cos update in consumer |
src/adapters/<agent>/** |
Only projects with that agent | cos update or re-run install.sh |
src/templates/<stack>/** |
Only projects using that stack | cos update + make manifest-regen |
src/cli/** |
ALL future cos invocations |
uv tool install --editable . |
Derived artifacts — never hand-edit: src/core/rules/{dimension-registry,skill-enforcement}.md, src/core/scaffold_manifest.json, src/adapters/*/*.template.*, tests/golden/** — regenerate via make regen-rules / manifest-regen / regen-adapter-templates.
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.
- yesterday First seen · 119 lines · 4,587 tokens per session scan A ed87c6087676
coding-os AGENTS.md is an instructions file published in the GitHub repository kouroshez/coding-os (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 4,587 tokens to every session, about $0.0229 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 2026-08-31.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
obsidian-llm-wiki AGENTS.md
Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
remnic AGENTS.md
Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
LeanKG AGENTS.md
Instructions for FreePeak/LeanKG, covering leankg — agent context, build & test, cli quick reference, mandatory: docker mcp project paths and tool discovery prefer-order.
ontology-atlas AGENTS.md
Instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.