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/davidmatousek/tachi/claude-mdgit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/davidmatousek/tachi/claude-md)<a href="https://agentmods.dev/instructions/davidmatousek/tachi/claude-md"><img src="https://agentmods.dev/badge/instructions/davidmatousek/tachi/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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
tachi 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agentic-oriented-development-kit CLAUDE.md — 94% identical, 11 lines differ
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 - tachi
Core Constraints
- Product-Led: Start with product vision, PRDs, and user stories
- Source of Truth:
.aod/spec.md - Validation Required: Run
/aod.analyzebefore PRs - Local-First: Always supports local
.aod/file workflows
Git Workflow
Always use feature branches: git checkout -b NNN-feature-name
- NNN = GitHub Issue number, zero-padded to 3 digits
- Never commit to main directly
- Draft PR opened at plan stage, marked ready at delivery
- Branch format:
NNN-descriptive-name(e.g.,021-feature-namefor Issue #21)
Project Structure
tachi/
├── .claude/ → Agents, skills, commands, design archetypes
├── .aod/ → Active feature workspace (spec.md, plan.md, tasks.md)
├── brands/ → Brand identity assets (vision + design tokens)
├── specs/ → Archived feature artifacts (per-feature history)
├── docs/ → Product, architecture, devops docs
├── scripts/ → init.sh, check.sh
├── stacks/ → Stack packs (conventions, personas, scaffolds)
└── CLAUDE.md → AI agent context
Note: Template provides methodology only. Users bring their own code.
Context Discovery
- Thinking Lenses:
docs/core_principles/README.md(5 Whys, Pre-Mortem, etc.) - Project Standards:
docs/standards/README.md(DoD, naming, git) - Product Docs:
docs/product/README.md - Architecture:
docs/architecture/README.md - Triad Guide:
docs/AOD_TRIAD.md - Constitution:
.aod/memory/constitution.md
Commands
PDL workflow (optional, before Triad):
/aod.discover→/aod.score
Post-init (recommended after make init):
/aod.foundation— Guided workshop: product vision + design identity
Triad workflow:
/aod.define→/aod.plan→/aod.build [--no-security] [--no-design-check] [--no-economy]- (
/aod.planchains: spec → project-plan → tasks automatically)
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 · 115 lines · 1,350 tokens per session scan A b74268d6c6ef
tachi CLAUDE.md is an instructions file published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,350 tokens to every session, about $0.0068 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 2026-09-03.
Other instructions, from other repositories
stride-gpt AGENTS.md
AGENTS.md instructions for mrwadams/stride-gpt, covering agents.md, what this project is, repository layout, how the agentic analysis works and progressive disclosure pattern.
Mingyi-Atlas AGENTS.md
AGENTS.md instructions for MingyiSecLab/Mingyi-Atlas, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
Mingyi-Atlas CLAUDE.md
Claude Code instructions for MingyiSecLab/Mingyi-Atlas, covering claude.md, project overview, common commands, architecture and modes and prompts.
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.
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.