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/sixbyfive/intent/claude-mdgit clone --depth 1 https://github.com/SixByFive/IntentWhat 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 | $0.02562 | $0.02562 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
Intent 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 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent — Claude Code Context
What this project is
Intent is a Git-native reasoning layer for software projects. It lives inside the repo as .intent/ and tracks the why behind code: plans, architectural decisions, constraints, and system context. It's designed to be read by both humans and AI agents.
The core idea: Git already tracks what changed. Intent tracks why it changed.
Monorepo structure
packages/
schemas/ — Zod schemas and TypeScript types for the .intent/ format (no deps on other packages)
core/ — All .intent/ file I/O, parsing, and git integration (depends on schemas)
cli/ — Commander-based CLI (depends on core, thin layer — no business logic here)
mcp/ — MCP server exposing Intent tools to AI agents (depends on core)
apps/
web/ — Hosted dashboard (future)
Dependency rule: schemas → core → cli/mcp. Never import cli into core. Never import core into schemas.
Tech stack
- TypeScript (strict, NodeNext modules)
- pnpm workspaces + Turborepo
- Zod for all schema validation
- Vitest for tests
- Commander for CLI
- simple-git for git integration
- gray-matter for frontmatter parsing
The .intent/ format
Every .intent/ file uses hybrid frontmatter markdown: structured YAML frontmatter + free-form markdown body. The YAML is the contract; the body is the reasoning.
Example plan file (.intent/plans/subscriptions.md):
---
id: plan-subscriptions
title: Marketplace subscription tiers
type: plan
status: active
created: 2024-01-01T00:00:00Z
updated: 2024-01-01T00:00:00Z
system: marketplace
decisions: [DEC-0001]
constraints: []
tags: [monetisation, marketplace]
---
## Goal
Add subscription tiers to the marketplace.
## Reason
Need monetisation while keeping core collecting accessible.
## Rules
- Free users: 5 listings
- Vendor users: unlimited listings
The only pure-JSON file is .intent/intent.json (project config).
Auto-generated indexes live in .intent/links/ — never edit these manually.
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.
- 2d ago First seen · 238 lines · 2,562 tokens per session scan A ebd68bedd573
Intent CLAUDE.md is an instructions file published in the GitHub repository SixByFive/Intent (4 stars, last pushed 2mo ago), licensed MIT. It adds 2,562 tokens to every session, about $0.0128 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
cli CLAUDE.md
Instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).
mcp-adr-analysis-server copilot-instructions.md
Instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.
nullius CLAUDE.md
Instructions for armanfatemi/nullius, covering nullius, commands, known-environmental test failures, evidence anchors — the house rule and dogfooding gates (ci runs all of these).
skilldrop AGENTS.md
Instructions for sananthanarayan/skilldrop, covering agents.md — guidance for autonomous coding agents, repo in one paragraph, golden rules, verified commands (do not invent variants) and consistency lint — run from the repo root before committing.
agent-skills AGENTS.md
Instructions for stark-ai-de/agent-skills, covering agent instructions and rules.
skilldrop CLAUDE.md
Instructions for sananthanarayan/skilldrop, covering claude.md, dogfooding a skill while you build it, then in a new claude code session in any repo, ${claudeskilldir} semantics and project settings.