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 skills add momentmaker/kaijutsu --skill security-auditgit clone --depth 1 https://github.com/momentmaker/kaijutsuWrote 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/skills/momentmaker/kaijutsu/security-audit)<a href="https://agentmods.dev/skills/momentmaker/kaijutsu/security-audit"><img src="https://agentmods.dev/badge/skills/momentmaker/kaijutsu/security-audit.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 | $0.00167 | $0.01561 |
| Opus 5 | $0.00084 | $0.00781 |
| Sonnet 5 | $0.00033 | $0.00312 |
| Haiku 4.5 | $0.00017 | $0.00156 |
Grade A, and why
security-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-audit
Adversarial multi-agent security review. Different from pr-review's broad code review — security-audit's three lenses are explicitly InfoSec-shaped, the severity vocab is CVSS-aligned, and the output is a threat model rather than a code-review findings list.
How agents collaborate
| Lens | Agent | Looks for |
|---|---|---|
| Auth + data flow | claude | Trust boundaries, identity propagation, authorization vs authentication, data flow to sinks |
| Injection + priv-esc | codex | SQL/command/XSS injection, path traversal, SSRF, race conditions, crypto misuse |
| Dependency + supply-chain | antigravity | Known CVEs, version drift, transitive trust, license compatibility |
Severity vocab (CVSS-aligned):
- critical — RCE, auth bypass, privilege escalation
- high — data breach, integrity violation
- medium — DoS, info disclosure, weak boundaries
- low — defense-in-depth gap, timing leak
- informational — worth noting but no exploitable path
Two input modes
# Diff mode — audit a PR
jutsu swarm security-audit --pr 42
# Diff mode — audit a local branch (no PR yet)
jutsu swarm security-audit --diff-from-branch origin/main
# Files mode — audit specific paths
jutsu swarm security-audit cmd/server/auth.go
# Files mode — audit a directory (multi-file concatenated)
jutsu swarm security-audit cmd/server/
# --quick to override the default --full mode
jutsu swarm security-audit --pr 42 --mode quick
# Iterate cheap on synth prompt
jutsu swarm security-audit --replay <key>
The two modes are mutually exclusive — passing --pr AND positional file paths errors with a "pick one" hint.
--full defaults ON
Unlike other presets, security-audit runs --full mode (with Pass-2 round-robin debate) by default. Security findings have asymmetric cost: false-positives erode user trust faster than missed issues. The debate round filters false-positives by having each agent critique its peers.
Override to --mode quick only when you're doing a fast first-pass scan.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 123 lines · 167 tokens per session scan A ec6bbe444c73
security-audit is a skill published in the GitHub repository momentmaker/kaijutsu (3 stars, last pushed 2mo ago), licensed MIT. It adds 167 tokens to every session and 1,561 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".