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.tasksgit 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.tasks)<a href="https://agentmods.dev/commands/davidmatousek/tachi/aod.tasks"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.tasks.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 | $0.00020 | $0.04920 |
| Opus 5 | $0.00010 | $0.02460 |
| Sonnet 5 | $0.00004 | $0.00984 |
| Haiku 4.5 | $0.00002 | $0.00492 |
Grade A, and why
aod.tasks 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aod.tasks — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 420 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).
Step 0: Parse --autonomous
- If
$ARGUMENTScontains--autonomous:- Set
autonomous = true - Strip
--autonomousfrom$ARGUMENTS(trim extra whitespace)
- Set
- Default:
autonomous = false
Step 0y: Parse --revision
- If
$ARGUMENTScontains--revision:- Set
revision_mode = true - Strip
--revisionfrom$ARGUMENTS(trim extra whitespace) - Read
.aod/revision-context.mdfor reviewer feedback (contains reviewer name, attempt number, artifact path, and full feedback text) - Store feedback as
revision_feedback - Clear governance cache explicitly: Call
aod_state_clear_governance_cache "tasks"so the upcoming triple review is treated as fresh regardless of mtime-staleness backstop. (Belt-and-suspenders: do NOT rely on the mtime backstop alone.)
- Set
- Default:
revision_mode = false
Overview
Generate an actionable, dependency-ordered tasks.md with automatic Triad triple sign-off governance.
Flow: Validate plan → Generate tasks → Triple review (parallel) → Handle blockers → Inject frontmatter → Generate assignments
Step 1: Validate Prerequisites
- Get branch:
git branch --show-current→ must matchNNN-*pattern - Find plan:
specs/{NNN}-*/plan.md→ must exist - Parse frontmatter: Verify
triad.pm_signoff.statusandtriad.architect_signoff.statusare APPROVED (or APPROVED_WITH_CONCERNS/BLOCKED_OVERRIDDEN) - If validation fails: Show error with required workflow order and exit
Step 2: Generate Tasks
If revision_mode == true (re-invocation after governance rejection):
- Read the existing tasks at
specs/{NNN}-*/tasks.md(do not start from scratch) - Read
revision_feedbackfrom.aod/revision-context.md - Apply targeted changes to address the specific issues raised by the reviewer
- Preserve sections the reviewer did not flag — only regenerate flagged sections
- Skip prerequisite loading (already in context) — jump directly to updating the flagged sections
- Proceed directly to Step 3 (Triple Sign-off) after updating the tasks
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.
- 4d ago First seen · 420 lines · 20 tokens per session scan A f5f3b30adf09
aod.tasks is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It adds 20 tokens to every session and 4,920 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.
README
Claude Code slash commands for the Unified Security Agent Platform (USAP). These commands let you load any USAP skill as a live LLM persona and run structured compliance tests — all inside a Claude Code session.
challenge
Run cs-security-analyst (AT workflow) against the Perfect Storm 8-vector crisis scenario and produce a 12-check mock comparison scorecard.
compare
Before/after comparison of zero-day-response SKILL.md v1 (broken) vs v2 (fixed) against the FortiGate zero-day scenario. Outputs a scored table.
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.