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/fixgit 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/fix)<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/fix"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/fix.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 | $0.00047 | $0.00479 |
| Opus 5 | $0.00023 | $0.00239 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
fix 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.
What it actually says
/fix — Guided Remediation
Apply a fix for the security issue described in $ARGUMENTS, or for the finding currently in context.
Built for MVP speed: resolve the issue with the smallest safe change, show the diff, keep moving.
Ground rules
- Fix only confirmed issues. If the finding is a hypothesis, say so and confirm it first — do not patch on a guess.
- Shortest structural fix wins. Prefer a framework-level control (parameterized query, auth middleware, validation at the boundary) over scattered one-off bandaids. No full refactors.
- Do not weaken anything else. The fix must not break existing behavior or remove another control.
- Never invent APIs. Use functions/config that exist in this codebase and its dependencies. Verify by reading before editing.
Steps
1. Confirm the issue
Restate the finding in one line: source → gap → sink. If not already confirmed in code, read the relevant lines now.
2. Choose the fix
State the fix and why it's the shortest credible one. Note any alternative you rejected and why (e.g. "escaping input" rejected in favor of "parameterized query — kills the class, not one payload").
3. Apply
Edit the working tree. For secrets: rotate is a human action — apply the code/config change and flag rotation as a required manual follow-up.
4. Show the diff
Present the exact change made, file by file.
5. Regression note
One line: what test or check would catch this if reintroduced. Offer to add it.
Guardrails
- If the fix touches auth, crypto, or payment flows, call it out explicitly and recommend a human review before deploy.
- If fixing correctly requires a decision only the team can make (which roles may access X, what the tenant model is), stop and ask rather than guessing.
- If more than ~3 files need changing, this is no longer a quick fix — summarize the needed change and confirm scope before proceeding.
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 · 44 lines · 47 tokens per session scan A f0b1bbc415a1
fix is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 479 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.