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/tta-lab/organon/agents-mdgit clone --depth 1 https://github.com/tta-lab/organonWrote 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/tta-lab/organon/agents-md)<a href="https://agentmods.dev/instructions/tta-lab/organon/agents-md"><img src="https://agentmods.dev/badge/instructions/tta-lab/organon/agents-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 | $0.01291 | $0.01291 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
organon 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 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Organon is a Go monorepo producing CLI tools for AI agents: src (tree-sitter source editing), skill (filesystem-based skill discovery), token (LLM token counting), project (project management CLI), and goal (Lenos session goal file management).
Essential Commands
make all # fmt, vet, tidy, build
make test # CGO_ENABLED=0 go test -v ./...
make build # CGO_ENABLED=0 go build ./cmd/...
make install # CGO_ENABLED=0 go install ./cmd/...
make ci # fmt, vet, lint, test, build
make ci-scope SCOPE_CMD=project SCOPE_PACKAGES='./cmd/project ./internal/project ./internal/config'
# scoped format check, vet, lint, test, and binary build
Architecture
Binaries
cmd/src/— tree-sitter symbol-aware file reading/editing with local path resolution and--jsonoutput for Pi extension adapterscmd/skill/— filesystem-based skill discovery plus read-only MCPcmd/token/— LLM token counting using tiktoken-go with cl100k_base tokenizer (Claude / GPT-4)cmd/project/— project management CLI: list, get, resolve, and jump to registered projectscmd/goal/— Lenos session goal file CLI: add/update/append/get/status via$LENOS_GOAL
Shared Packages
internal/id/— base62 ID generation and collision resolutioninternal/tree/— generic box-drawing tree rendererinternal/indent/— file indent-style detection (layered: hardcoded table for opinionated languages, per-file majority scan for open languages) and reindent transforminternal/skill/— filesystem-based skill discovery, frontmatter parsing, and shared CLI/MCP search behaviorinternal/token/— LLM token counting with tiktoken-go; sync.OnceValues lazy init, regex fallbackinternal/srcview/— trusted source outlines and line-oriented reads shared by the CLI and the Pi src extensioninternal/truncate/— Pi-equivalent head truncation (2,000 lines / 50 KB) for CLI JSON output
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 · 115 lines · 1,291 tokens per session scan A 15ae2ef0f324
organon AGENTS.md is an instructions file published in the GitHub repository tta-lab/organon (5 stars, last pushed 6d ago), licensed MIT. It adds 1,291 tokens to every session, about $0.0065 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
web AGENTS.md
AGENTS.md instructions for GuionAI/web, covering agents.md, platform validation and dsh alpha.3 loader validation.
coding-tools-mcp AGENTS.md
AGENTS.md instructions for xyTom/coding-tools-mcp, covering coding tools mcp repository guide, repository map and standing rules.
distill-kura AGENTS.md
AGENTS.md instructions for lna-lab/distill-kura, covering agents.md — working on distill-kura, what this project is, boundaries, the one rule that outranks the others and things that must not grow here.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.