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/coldtatooine/vuln-skill-pack/findinggit 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/finding)<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/finding"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/finding.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 | $0.00043 | $0.00464 |
| Opus 5 | $0.00022 | $0.00232 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
finding 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.
What it actually says
/finding — Format a Security Finding
Write up the current finding as a report card.
If $ARGUMENTS is provided, use it as the finding title (strip flags first). Otherwise, derive it from context.
Mode: if $ARGUMENTS contains --quick, use the Quick format. Otherwise use the Full format.
Ground rules
- Only document what you've actually confirmed in the code. Label guesses as hypotheses.
- Don't inflate severity — base it on a realistic exploit path, not theoretical worst case.
- The fix should be the shortest credible solution, not a full refactor.
Quick format (--quick)
Three lines, for day-to-day triage speed:
[Severity] TITLE — file:line
Risk: [what an attacker gets, one line]
Fix: [shortest credible fix, one line]
Full format (default)
[TITLE]
Severity: Critical / High / Medium / Low Confidence: High / Medium / Low CWE: [number and name] Affected: [file(s), function(s), line range(s)] Attack surface: [entry point — route, handler, CLI arg, agent interface, etc.] Prerequisites: [what the attacker needs — auth? network access? specific role?]
Root cause: [One paragraph. Source → missing validation → sink. Be specific.]
Evidence: [Exact code behavior. Quote or reference the relevant lines. Explain why it's vulnerable.]
Safe reproduction: [Minimal steps to confirm the issue without causing harm.]
Impact: [What an attacker realistically achieves. No exaggeration.]
Fix: [Shortest structural fix. Prefer framework-level controls over one-off bandaids.]
Regression test: [What test would catch this if reintroduced.]
If the issue is not fully confirmed, add at the top:
Status: Hypothesis — [what evidence is still missing]
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 · 68 lines · 43 tokens per session scan A d627bbfc22c0
finding is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 464 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.