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/djadmin/fort/fort-auditgit clone --depth 1 https://github.com/djadmin/fortWhat 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 | $0.00015 | $0.00331 |
| Opus 5 | $0.00008 | $0.00166 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
fort-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run a read-only macOS security audit with fort and present it so the user actually
understands where they stand. Do not change anything in this command — auditing is
read-only.
- Confirm fort is installed (
fort --version); if not, tell the userbrew install djadmin/tap/fortand stop. - Run
fort --json. If the user passed check IDs in$ARGUMENTS, scope it:fort --only $ARGUMENTS --json. - Lead with the score and a one-line verdict.
- Walk the findings in order of real-world risk — what exposes the machine first,
lower-risk items after. For each failing or warning check, say what it is, where it
stands (
currentvsexpected, and theevidencefort captured), and why it matters. Note which are auto-fixable. - Briefly note what passed.
- Offer next steps: preview a fix (
fort --only <id> --dry-run) or, if they want it, an evidence report (fort --report). Don't apply anything yet — fixes happen only after the user reviews a preview and explicitly says yes.
Use reference/checks.md from the fort skill for the "why it matters" detail.
$ARGUMENTS
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.
- 2d ago First seen · 29 lines · 15 tokens per session scan A 10f4a910d736
fort-audit is a command published in the GitHub repository djadmin/fort (78 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 331 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
init
Documentation for trestle.core.commands.init module.
onboard-interactive
Interactive customer onboarding with Step 0 independent verification (dialog-based, 17 stagegates).
monitor
AML transaction monitoring and suspicious activity reporting.
Update SSP From Evidence
Use new evidence, findings, or POA&M information to update an existing OSCAL SSP while preserving traceability.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
research
Start or resume an academic research project — idea through literature, methodology, writing, feedback, and publishing.