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.
git clone --depth 1 https://github.com/coldtatooine/vuln-skill-packWrote 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/coldtatooine/vuln-skill-pack/triage)<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/triage"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/triage.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 | $0.00042 | $0.00522 |
| Opus 5 | $0.00021 | $0.00261 |
| Sonnet 5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
triage 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 8d 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
/triage — Launch Decision Triage
Take the findings in context (or in $ARGUMENTS) and answer the founder's real question: what must be fixed before we ship, and what can wait?
MVPs don't fix everything before launch. The goal is an honest, defensible risk decision — ship fast without shipping a breach.
Ground rules
- Base severity on a realistic exploit path, not worst-case theory.
- Weigh blast radius for this product: user data at risk, money movement, account takeover, full compromise.
- "Accept risk" is a valid outcome — but only when documented, bounded, and owned.
Classify each finding into one bucket
🔴 Blocks launch — fix before public deploy
Any of:
- Confirmed path to user data, credentials, money, or account takeover.
- Leaked secret that is live / in git history / shipped to client (rotate + remove now).
- Unauthenticated access to sensitive data or actions.
- Remote code / command / SQL execution.
- Payment amount or entitlement trusted from the client.
🟡 Fix this week — ship, but on a clock
- Real issues with a narrower path or lower impact.
- Missing defense-in-depth (rate limiting, security headers, log redaction).
- Medium-severity injection behind auth.
- Assign an owner and a date.
🟢 Accept documented risk — track, don't block
- Low impact, hard to reach, or requires unrealistic preconditions.
- Best-practice gaps with no concrete exploit.
- Record: what it is, why it's accepted, what would change the decision, who owns revisiting it.
Output
LAUNCH DECISION: GO / GO-WITH-FIXES / NO-GO
🔴 Blocks launch (N)
- [finding] — file:line — fix: [shortest] — owner: [?]
🟡 Fix this week (N)
- [finding] — file:line — by: [date] — owner: [?]
🟢 Accepted risk (N)
- [finding] — why accepted — revisit when: [trigger]
GO-WITH-FIXES means: clear the 🔴 list, then ship. Hand each 🔴 to /fix.
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.
- 8d ago First seen · 58 lines · 42 tokens per session scan A 7470669f8db1
triage is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 522 once invoked, about $0.0002 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 commands, from other repositories
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.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.