tachi: Skill for Claude Code

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

~aod-plan is a skill for Claude Code from davidmatousek/tachi. It costs 64 tokens per session (2,740 once invoked), scanned A, original, Apache-2.0.

A planning coordinator that runs specification, project-plan, and task-planning steps in order. It pauses when a review rejects a step and continues only after approval.

In plain words
What is it for?
It is for turning a feature idea into a reviewed specification, architecture plan, and implementation task list.
Why use it?
It keeps the planning process ordered and prevents later planning work from starting while an earlier document still needs changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 →

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-plan/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-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-plan.svg)](https://agentmods.dev/skills/davidmatousek/tachi/aod-plan)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/aod-plan"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,740 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.
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 $0.00064 $0.02740
Opus 5 $0.00032 $0.01370
Sonnet 5 $0.00013 $0.00548
Haiku 4.5 $0.00006 $0.00274

Measured 3d ago against content hash ff1811f3b4b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

~aod-plan 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 3d 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-plan — 100% identical, 0 lines differ
.claude/skills/~aod-plan/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Stage Orchestrator Skill

Purpose

Orchestrates the full Plan stage by running spec → project-plan → tasks in sequence. After each sub-step completes and its governance review passes (APPROVED), the orchestrator automatically advances to the next sub-step. If any review returns CHANGES_REQUESTED or BLOCKED, the orchestrator stops and reports the rejection so the user can fix and re-run /aod.plan to resume.

With 1M context, all three artifacts and their reviews fit comfortably in a single session.

How It Works

Step 1: Determine Feature Context

  1. Get branch: git branch --show-current → extract NNN prefix
  2. If on main and a PRD exists (e.g., docs/product/02_PRD/{NNN}-*.md), automatically create the feature branch (git checkout -b {NNN}-{kebab-name}) per git workflow rules. Do NOT ask the user — feature branches are mandatory, not optional.
  3. Open Draft PR: After creating the branch, push it and open a draft PR so work is visible early:
    git commit --allow-empty -m "chore({NNN}): open feature branch"
    git push -u origin {NNN}-{kebab-name}
    gh pr create --draft \
      --title "{NNN}: {Feature Name}" \
      --body "Draft PR for feature {NNN}. Opened automatically at plan stage."
    
    If gh is unavailable, skip silently (graceful degradation). Store the PR number for later use.
  4. Derive specs directory: specs/{NNN}-*/
  5. If no specs directory found, check .aod/spec.md as fallback
  6. If no feature context found: warn and suggest /aod.define first

Step 2: Read Artifact States

For each artifact (spec.md, plan.md, tasks.md), determine its approval status:

  1. Check file existence — if file cannot be read (missing, permissions, encoding), treat as "does not exist"
  2. Parse YAML frontmatter — extract the triad: block between --- delimiters
  3. Extract sign-off status — read triad.{role}_signoff.status for the required reviewers

Step 3: Evaluate Frontmatter (with error handling)

Read the full file on GitHub · 194 lines

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. 3d ago First seen · 194 lines · 64 tokens per session scan A ff1811f3b4b7

Subscribe to this mod's changes

~aod-plan is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 24d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,740 once invoked, about $0.0003 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.