tachi: Skill for Claude Code

.claude/skills/aod-orchestrate/SKILL.md

aod-orchestrate is a skill for Claude Code from davidmatousek/tachi. It costs 110 tokens per session (10,187 once invoked), scanned A, original, Apache-2.0.

A coordinator for implementing several GitHub Issues in priority-based waves. It groups issues by ICE priority, where ICE combines impact, confidence, and ease, then creates tasks and starts parallel work sessions.

In plain words
What is it for?
Use it to fetch selected issues, organize P0, P1, and P2 work into sequential waves, execute each wave, and monitor completion.
Why use it?
It removes the manual planning and coordination needed to decide which features run first and which can run at the same time.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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-orchestrate/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-orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-orchestrate.svg)](https://agentmods.dev/skills/davidmatousek/tachi/aod-orchestrate)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/aod-orchestrate"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/aod-orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 10 findings, 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 Tool Misuse · line 483
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Supply Chain · line 567
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • medium Excessive Agency · line 73
    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.
  • medium Excessive Agency · line 76
    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.
  • medium Excessive Agency · line 377
    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.
  • medium Data Exfiltration · line 128
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Excessive Agency · line 377
    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.
  • medium Excessive Agency · line 395
    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.
  • medium Data Exfiltration · line 567
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 712
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00110 $0.10187
Opus 5 $0.00055 $0.05094
Sonnet 5 $0.00022 $0.02037
Haiku 4.5 $0.00011 $0.01019

Measured 8d ago against content hash 3d02470843d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aod-orchestrate scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sf "${AOD_API_URL:-http://localhost:8000}/api/v1/projects/{project_id}" -H "X-AOD-Source: skill"
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/aod-orchestrate/SKILL.md · 986 lines

How it starts

The opening of the file, as written. The whole thing — 986 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aod.orchestrate Skill

Purpose

Orchestrate multiple features from /aod.blueprint output as priority-ordered parallel waves. The skill auto-detects the project, fetches actionable issues, groups them by ICE priority tier, and executes waves sequentially via the batch spawn API with governance checkpoints at tier boundaries.

Flow: Parse flags --> Auto-detect project --> Check idempotency --> Fetch issues --> Plan waves --> Confirm --> Execute waves --> Report completion


Step 0: Capture Start Time

Record the orchestration start time for duration calculation in the completion report.

Run the following command via Bash tool and store the result:

date +%s

Store this value as start_time for use in Step 8 (Completion Reporter).


Step 1: Parse Arguments

Parse user arguments from the skill invocation.

User Input

$ARGUMENTS

1.1: Parse --issues flag

Check if $ARGUMENTS contains --issues:

  1. If $ARGUMENTS contains --issues N,N,N (comma-separated issue numbers):
    • Extract the comma-separated list of issue numbers
    • Set selected_issues to the parsed list of integers
    • Strip --issues N,N,N from $ARGUMENTS (trim extra whitespace)
  2. If $ARGUMENTS does NOT contain --issues:
    • Set selected_issues to empty (all issues)

1.2: Parse --dry-run flag

Check if $ARGUMENTS contains --dry-run:

  1. If present:
    • Set dry_run = true
    • Strip --dry-run from $ARGUMENTS
  2. If not present:
    • Set dry_run = false

1.3: Parse --yes flag

Check if $ARGUMENTS contains --yes:

  1. If present:
    • Set auto_confirm = true
    • Strip --yes from $ARGUMENTS
  2. If not present:
    • Set auto_confirm = false

Step 2: Project Auto-Detection

Resolve the active orchestrator project from local context. Detection follows a priority order with fallback.

2.1: Read config file

Run the following command via Bash tool:

cat .aod/config.json 2>/dev/null

Read the full file on GitHub · 986 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. 8d ago First seen · 986 lines · 110 tokens per session scan A 3d02470843d8

Subscribe to this mod's changes

aod-orchestrate is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 26d ago), licensed Apache-2.0. It adds 110 tokens to every session and 10,187 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.