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.buildgit 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.build)<a href="https://agentmods.dev/commands/davidmatousek/tachi/aod.build"><img src="https://agentmods.dev/badge/commands/davidmatousek/tachi/aod.build.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 | $0.00013 | $0.11031 |
| Opus 5 | $0.00006 | $0.05515 |
| Sonnet 5 | $0.00003 | $0.02206 |
| Haiku 4.5 | $0.00001 | $0.01103 |
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 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.build — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 757 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 Arguments
Parse optional flags from $ARGUMENTS. Flags can appear anywhere in the arguments string.
Step 0a: Parse --no-security
-
If
$ARGUMENTScontains--no-security:- Set
skip_security = true - Strip
--no-securityfrom$ARGUMENTS(trim extra whitespace) - Continue to Step 0b with remaining arguments
- Set
-
If
$ARGUMENTSdoes NOT contain--no-security:- Set
skip_security = false - Continue to Step 0b with
$ARGUMENTSunchanged
- Set
Step 0b: Parse --orchestrated
- If
$ARGUMENTScontains--orchestrated:- Set
orchestrated = true - Strip
--orchestratedfrom$ARGUMENTS(trim extra whitespace)
- Set
- If
$ARGUMENTSdoes NOT contain--orchestrated:- Set
orchestrated = false
- Set
Step 0c: Parse --autonomous
- If
$ARGUMENTScontains--autonomous:- Set
autonomous = true - Strip
--autonomousfrom$ARGUMENTS(trim extra whitespace)
- Set
- If
$ARGUMENTSdoes NOT contain--autonomous:- Set
autonomous = false
- Set
Step 0d: Parse --no-design-check
-
If
$ARGUMENTScontains--no-design-check:- Set
skip_design_check = true - Strip
--no-design-checkfrom$ARGUMENTS(trim extra whitespace) - Continue to Step 0e with remaining arguments
- Set
-
If
$ARGUMENTSdoes NOT contain--no-design-check:- Set
skip_design_check = false - Continue to Step 0e with
$ARGUMENTSunchanged
- Set
Step 0e: Parse --no-tests
-
If
$ARGUMENTScontains--no-tests:- Set
skip_tests = true - Strip
--no-testsfrom$ARGUMENTS(trim extra whitespace) - Continue to Step 0f with remaining arguments
- Set
-
If
$ARGUMENTSdoes NOT contain--no-tests:- Set
skip_tests = false - Continue to Step 0f with
$ARGUMENTSunchanged
- Set
Step 0f: Parse --require-tests
- If
$ARGUMENTScontains--require-tests:- Set
require_tests = true - Strip
--require-testsfrom$ARGUMENTS(trim extra whitespace) - Conflict check: If both
skip_testsandrequire_testsare true,skip_teststakes precedence (test execution is skipped entirely). Display:"Warning: --no-tests and --require-tests both present. --no-tests takes precedence (tests skipped)." - Continue to Step 0g with remaining arguments
- Set
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 · 757 lines · 13 tokens per session scan A 71a43c1ab823
aod.build 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 11,031 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.