tachi: Skill for Claude Code

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

~aod-discover is a skill for Claude Code from davidmatousek/tachi. It costs 103 tokens per session (6,379 once invoked), scanned A, original, Apache-2.0.

A discovery workflow for capturing project ideas, rating their priority, gathering evidence, and checking them with product-management rules. It supports full discovery, a fast path for pre-approved ideas, idea capture alone, or validation alone.

In plain words
What is it for?
It is for recording ideas, assigning ICE scores, collecting supporting evidence, validating proposed work, and producing user stories.
Why use it?
It turns loosely formed ideas into clearer, prioritised work items with user stories and review results.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

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/create-issue.sh --title "Feature title" --body "Markdown body" --stage discover.

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-discover/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-discover

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-discover.svg)](https://agentmods.dev/skills/davidmatousek/tachi/aod-discover)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/aod-discover"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,379 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 medium

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 →

  • medium Excessive Agency · line 13
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00103 $0.06379
Opus 5 $0.00051 $0.03189
Sonnet 5 $0.00021 $0.01276
Haiku 4.5 $0.00010 $0.00638

Measured 4d ago against content hash 121464ca649c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

~aod-discover 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:

.claude/skills/~aod-discover/SKILL.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AOD Discover Skill

Purpose

Unified discovery skill for the AOD Lifecycle's Discover stage. Handles idea capture, ICE scoring, evidence gathering, and PM validation with 3 entry points:

  • /aod.discover — Full flow: capture idea + ICE score + evidence + PM validation + user story
  • /aod.discover --seed — Seed mode: fast-track pre-vetted ideas (auto ICE, skip prompts, skip PM)
  • /aod.idea — Capture only: capture idea + ICE score + evidence (no PM validation)
  • /aod.validate — Validate only: submit existing idea for PM review + user story generation

Entry Point Detection

Determine the entry point from the invoking command:

  • If invoked via /aod.discover --seed → run Seed Mode (Steps 1, 2, 5a, 5b, 8-seed)
  • If invoked via /aod.discover → run Full Flow (Steps 1-8)
  • If invoked via /aod.idea → run Capture Only (Steps 1-5)
  • If invoked via /aod.validate → run Validate Only (Steps 6-8)

--seed Flag Detection

Check if arguments contain --seed flag. If present:

  • Remove --seed from the idea description text
  • Set entry point to Seed Mode
  • Seed mode is designed for pre-vetted ideas (e.g., from consumer guides) that don't need scoring or validation

Critical Constraints

MUST use .aod/scripts/bash/create-issue.sh for ALL GitHub Issue creation. NEVER call gh issue create directly.

Why: Direct gh issue create bypasses the board sync pipeline, causing issues to silently disappear from the project board. The create-issue.sh script delegates to aod_gh_create_issue() which includes automatic board placement via aod_gh_add_to_board(). See KB Entry #20 for root cause analysis.

Prohibited pattern (DO NOT use):

# WRONG — bypasses board sync
gh issue create --title "..." --label "stage:discover" --body "..."

Required pattern:

# CORRECT — includes board sync automatically
bash .aod/scripts/bash/create-issue.sh --title "Feature title" --body "Markdown body" --stage discover

Read the full file on GitHub · 591 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 · 591 lines · 103 tokens per session scan A 121464ca649c

Subscribe to this mod's changes

~aod-discover is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 26d ago), licensed Apache-2.0. It adds 103 tokens to every session and 6,379 once invoked, about $0.0005 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.