tachi: Skill for Claude Code

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

~aod-build is a skill for Claude Code from davidmatousek/tachi. It costs 56 tokens per session (2,510 once invoked), scanned A, original, Apache-2.0.

A checkpoint-report workflow for multi-phase software projects. It summarizes completed and remaining tasks, progress, technical work, quality measures, and instructions for resuming later.

In plain words
What is it for?
Use it after a phase, user story, or critical milestone, or before pausing implementation, to generate a progress report from a task file.
Why use it?
It preserves project context at milestones or pauses, so work can restart without reconstructing what happened.

Skill for Claude Code

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

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 reads a path above its own folder, which exists only inside the repository. The line is --tasks-file ../../specs/{feature-id}/tasks.md \.

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-build/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-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-build.svg)](https://agentmods.dev/skills/davidmatousek/tachi/aod-build)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/aod-build"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,510 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 pass 7 Sept 2026
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 $0.00056 $0.02510
Opus 5 $0.00028 $0.01255
Sonnet 5 $0.00011 $0.00502
Haiku 4.5 $0.00006 $0.00251

Measured 4d ago against content hash 610e720fee5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

~aod-build 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/analyze_tasks.py, scripts/generate_checkpoint.py, scripts/update_index.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/~aod-build/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Checkpoint Skill

Purpose

Automatically generate standardized checkpoint reports that document implementation progress at strategic milestones. Each report includes completed tasks, remaining work, technical achievements, knowledge base entries, quality metrics, and resume instructions.

When to Use

Create a checkpoint at:

  1. Complete phase finish - All tasks in a phase marked complete
  2. User story completion - Entire user story implemented and tested
  3. Critical milestone - Core functionality ready (e.g., MVP core)
  4. Before pausing - Stopping for review, testing, or user feedback
  5. After architect review - Major approval/sign-off received

How to Use

Quick Usage

# Navigate to skill directory
cd .claude/skills/~aod-build

# Generate checkpoint (interactive prompts will follow)
python scripts/generate_checkpoint.py \
  --tasks-file ../../specs/{feature-id}/tasks.md \
  --output-dir ../../specs/{feature-id} \
  --description "{Phase-Description}"

Step-by-Step Process

  1. Analyze completion status

    # Script automatically:
    # - Reads tasks.md
    # - Counts [X] completed vs [ ] pending
    # - Calculates progress percentage
    # - Identifies completed phases
    # - Determines task range
    
  2. Provide context when prompted

    Key achievements (3-5 bullet points):
    > - Achievement 1
    > - Achievement 2
    > - Achievement 3
    
    Knowledge base entries captured (count or 'none'):
    > 2
    
    [For each KB entry, provide: Title, Problem, Solution]
    
  3. Review generated report

    # Output: CHECKPOINT-{NN}_{Description}_{TaskRange}.md
    # Location: specs/{feature-id}/
    
  4. Verify index updated

    # Check: CHECKPOINTS_README.md includes new checkpoint
    

Checkpoint Naming Convention

Format: CHECKPOINT-{NN}_{Phase-Description}_{TaskRange}.md

Components:

  • {NN}: Sequential checkpoint number (01, 02, 03...) - auto-detected
  • {Phase-Description}: Milestone name (e.g., "Phase1-2-Complete", "US1-Complete")
  • {TaskRange}: Task IDs covered (e.g., "T001-T030")

Read the full file on GitHub · 338 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. 4d ago First seen · 338 lines · 56 tokens per session scan A 610e720fee5e

Subscribe to this mod's changes

~aod-build is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 26d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,510 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.