tachi: Command for Claude Code

.claude/commands/aod.deliver.md

aod.deliver is a command for Claude Code from davidmatousek/tachi. It costs 16 tokens per session (4,176 once invoked), scanned A, original, Apache-2.0.

A feature-closing command that checks whether work is ready to close, updates related documentation, cleans up, and commits the changes.

In plain words
What is it for?
Use it after a feature is implemented and its pull request—a request to merge code into the main branch—has been merged.
Why use it?
It helps prevent unfinished tasks, missing documentation, or uncommitted changes from being mistaken for completed work.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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/commands/aod.deliver.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.deliver

README.md
[![agentmods](https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.deliver.svg)](https://agentmods.dev/commands/davidmatousek/tachi/aod.deliver)
Your own site
<a href="https://agentmods.dev/commands/davidmatousek/tachi/aod.deliver"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.deliver.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,176 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 $0.00016 $0.04176
Opus 5 $0.00008 $0.02088
Sonnet 5 $0.00003 $0.00835
Haiku 4.5 $0.00002 $0.00418

Measured 7d ago against content hash 98a8224dca3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aod.deliver 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 7d 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:

.claude/commands/aod.deliver.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Close a completed feature by validating readiness, launching parallel documentation agents, performing cleanup, and committing all changes.

Input

$ARGUMENTS

Feature number (e.g., 007 or 007-phase-brain-rag). If omitted, detect from recent PRs or prompt.

Step 0: Parse Flags

  1. If $ARGUMENTS contains --autonomous:
    • Set autonomous = true
    • Strip --autonomous from $ARGUMENTS (trim extra whitespace)
    • Default: autonomous = false
  2. If $ARGUMENTS contains --require-tests:
    • Set require_tests = true
    • Strip --require-tests from $ARGUMENTS (trim extra whitespace)
    • Default: require_tests = false

Step 1: Validate Closure Readiness

Run these checks (in parallel where possible):

Check Command Pass Condition
Feature exists ls specs/*{NUMBER}* Directory found
PR merged git branch -a | grep {NUMBER} Branch NOT found (deleted after merge)
Tasks complete grep "^\- \[ \]" specs/{FEATURE}/tasks.md Zero incomplete tasks

Branch & PR Handling (Automatic)

Per git workflow rules, feature branches require PRs — handle this automatically without prompting:

  1. If uncommitted changes exist: Stage and commit all changes with a conventional commit message
  2. If branch is not pushed: Push to remote with -u flag
  3. If no PR exists: Create one via gh pr create with a summary of all branch commits
  4. If PR exists but not merged: Merge it via gh pr merge --squash --delete-branch
  5. If PR already merged and branch deleted: Proceed directly

Only prompt the user if an automated step fails (e.g., merge conflicts, CI failure).

Other Validation Failures

  • Tasks incomplete:
    • If autonomous == true: Auto-select "Proceed anyway". Display: "Auto-selected: Proceed past incomplete tasks (autonomous mode)"
    • Else: (A) Mark complete, (B) Abort, (C) Proceed anyway

Step 2: Gather Feature Context

Read specs/{FEATURE}/tasks.md and specs/{FEATURE}/spec.md to extract:

Read the full file on GitHub · 307 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. 7d ago First seen · 307 lines · 16 tokens per session scan A 98a8224dca3d

Subscribe to this mod's changes

aod.deliver is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 25d ago), licensed Apache-2.0. It adds 16 tokens to every session and 4,176 once invoked, about $0.0001 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 2026-08-30.