Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/davidmatousek/tachi/aod.discovergit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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.
[](https://agentmods.dev/commands/davidmatousek/tachi/aod.discover)<a href="https://agentmods.dev/commands/davidmatousek/tachi/aod.discover"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.discover.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.01142 |
| Opus 5 | $0.00006 | $0.00571 |
| Sonnet 5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00001 | $0.00114 |
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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aod.discover — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Consider user input before proceeding (if not empty).
Overview
Captures a raw feature idea, scores it with ICE (Impact, Confidence, Effort), and creates a GitHub Issue for lifecycle tracking.
Source of truth: GitHub Issues with stage:* labels. BACKLOG.md is auto-generated.
Flow: Parse idea → Generate ID from GitHub Issues → Capture source → ICE scoring → Evidence → Auto-defer gate → Create GitHub Issue → Regenerate BACKLOG.md → Report result
Flags
--seed: Fast-track mode for pre-vetted ideas. Skips ICE prompts, evidence, source, and PM validation. Auto-assigns P1 defaults (I:8 C:7 E:7 = 22). Usage:/aod.discover --seed My feature idea--autonomous: Auto-select defaults for all interactive prompts (used byaod.runorchestrator). See Step 0.
Step 0: Parse --autonomous
- If
$ARGUMENTScontains--autonomous:- Set
autonomous = true - Strip
--autonomousfrom$ARGUMENTS(trim extra whitespace)
- Set
- Default:
autonomous = false
Step 1: Validate Input
- Parse idea description from
$ARGUMENTS - If empty: Ask the user to describe their idea before proceeding
Step 2: Execute Idea Capture
Follow the workflow defined in the ~aod-discover skill (.claude/skills/~aod-discover/SKILL.md):
- Create GitHub Issue and use the auto-assigned Issue number as the canonical ID
- Capture source via AskUserQuestion (Brainstorm / Customer Feedback / Team Idea / User Request)
- If
autonomous == true: Auto-select"Team Idea". Display:"Auto-selected: Team Idea (autonomous mode)"
- If
- ICE scoring via AskUserQuestion (Impact, Confidence, Effort — each H9/M6/L3 or custom 1-10)
- If
autonomous == true: Auto-assign medium defaults: Impact=6, Confidence=6, Effort=6 (total=18). Display:"Auto-selected: ICE 6/6/6 = 18 (autonomous mode)"
- If
- Evidence prompt via AskUserQuestion
- If
autonomous == true: Auto-provide"Automated discovery via aod.run". Display:"Auto-selected: automated evidence (autonomous mode)"
- If
- Compute ICE total, apply auto-defer gate (< 12 = Deferred, >= 12 = Scoring)
- Create GitHub Issue with structured body and
stage:discoverlabel - Regenerate BACKLOG.md via
.aod/scripts/bash/backlog-regenerate.sh - Report result with ID, ICE breakdown, priority tier, and next step guidance
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.
- 5d ago First seen · 82 lines · 13 tokens per session scan A 468ed9f69fe5
aod.discover is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 23d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,142 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.
Other commands, from other repositories
fortigate
Run cs-security-analyst (AT + CA workflows) against the Fintech FortiGate zero-day scenario and produce a 7-task scorecard.
challenge
Run cs-security-analyst (AT workflow) against the Perfect Storm 8-vector crisis scenario and produce a 12-check mock comparison scorecard.
test
Run a USAP skill against the FortiGate zero-day test scenario and produce a 6-problem compliance scorecard.
run
Load a USAP skill SKILL.md and activate it as your operating persona. Argument: skill slug.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.