tachi: Skill for Claude Code

.claude/skills/~aod-run/SKILL.md

~aod-run is a skill for Claude Code from davidmatousek/tachi. It costs 72 tokens per session (10,107 once invoked), scanned A, original, Apache-2.0.

A lifecycle coordinator that connects six project stages, from discovering an idea through documenting the finished work. It saves its progress so a paused run can continue later and requires reviews between stages.

In plain words
What is it for?
It is for starting or resuming feature work, running discovery, definition, planning, building, delivery, and documentation steps, and checking lifecycle status.
Why use it?
It keeps work moving through a defined process and preserves the current position when a session ends or a review requires changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is davidmatousek/tachi's own configuration. It tells Claude Code how to work on tachi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tachi configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .aod/scripts/bash/backlog-regenerate.sh 2>/dev/null || true.

Reuse

Borrowing it

Nothing to install: this file belongs to davidmatousek/tachi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/davidmatousek/tachi/main/.claude/skills/~aod-run/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Wrote 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.

agentmods badge for ~aod-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-run.svg)](https://agentmods.dev/skills/davidmatousek/tachi/aod-run)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/aod-run"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Data Exfiltration · line 367
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.10107
Opus 5 $0.00036 $0.05053
Sonnet 5 $0.00014 $0.02021
Haiku 4.5 $0.00007 $0.01011

Measured 4d ago against content hash bd890355e021, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

~aod-run 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • ~aod-run — 100% identical, 0 lines differ
.claude/skills/~aod-run/SKILL.md · 694 lines

How it starts

The opening of the file, as written. The whole thing — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Lifecycle Orchestrator Skill

Purpose

Single-command lifecycle orchestrator that chains all 6 AOD stages autonomously, pausing at governance gates for Triad sign-offs and persisting state to disk for session resilience. After Deliver completes, Document runs automatically as Stage 6.

Entry Points:

  • Raw idea: "description" → start at Discover
  • Issue number: #NNN or NNN → resume from issue's current stage
  • Resume: --resume → continue from last state checkpoint
  • Status: --status / --status #NNN → read-only display

State File: .aod/run-state.json (atomic write-then-rename via run-state.sh)

Section Purpose Location
Step 1: Route by Mode Entry point routing This file
Step 2: Core State Machine Loop Central orchestration logic This file
Plan Substage Tracking Spec → project_plan → tasks This file
Stage Skill Mapping Stage-to-skill invocation table This file
Post-Stage Context Extraction Artifact discovery after each stage This file
Stage Map Display Visual progress indicators This file
Transition Messages Stage transition headers This file
GitHub Integration Label updates after stage completion This file
Error Logging Error/event capture in state file This file
Governance Gate Detection Reading approval/rejection from frontmatter references/governance.md
Governance Tier Light/Standard/Full gate rules references/governance.md
Rejection / Retry / Circuit Breaker / Blocked Governance result handling references/governance.md
New Idea / Issue / Resume / Status Entry Mode-specific handlers references/entry-modes.md
Dry-Run Entry --dry-run preview handler (read-only) references/dry-run.md
Corrupted State / Lifecycle Complete Error and completion handlers references/error-recovery.md

Read the full file on GitHub · 694 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 4d ago First seen · 694 lines · 72 tokens per session scan A bd890355e021

Subscribe to this mod's changes

~aod-run is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 25d ago), licensed Apache-2.0. It adds 72 tokens to every session and 10,107 once invoked, about $0.0004 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.