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 skills/hoavdc/codexkit/codexkit-bug-huntnpx skills add hoavdc/CodexKit --skill codexkit-bug-huntgit clone --depth 1 https://github.com/hoavdc/CodexKitWhat 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 | $0.00027 | $0.00421 |
| Opus 5 | $0.00014 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
codexkit-bug-hunt 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 yesterday.
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
Bug Hunt
Use this skill when a report says something is broken and you need disciplined debugging rather than guesswork.
Workflow
- Capture exact observed behavior and expected behavior.
- Reproduce with the cheapest reliable path.
- Narrow the failure boundary before editing code.
- Patch the smallest credible cause.
- Verify the original failure and nearby regressions.
Required outputs
- reproduction path
- root-cause hypothesis
- patch summary
- verification notes
Avoid
- fixing symptoms without a reproduction
- stacking unrelated cleanup into the bug fix
- claiming a root cause without evidence
Quality Criteria
- Every finding is tied to a specific evidence source (log, test, metric)
- Pass/fail criteria are binary and measurable — no subjective judgments
- Severity levels are assigned with clear thresholds
- Remediation steps are provided for all critical and high findings
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Are all pass/fail criteria applied against the correct standard or rule? |
| Completeness | Were all required dimensions or checklist items evaluated? |
| Context-fit | Does the verification scope match the actual risk level of the deliverable? |
| Consequence | If this passed verification but had a hidden flaw, what is the worst-case impact? |
Edge Cases
- Incomplete data for full assessment — Document which checks were limited and flag for re-verification when data becomes available.
- Ambiguous pass/fail criteria — Request clarification from the standard owner before scoring. Mark as 'Needs Review'.
- Multiple overlapping standards — Identify the governing standard and note where others diverge.
Changelog
- v1.0.0 — Initial release
What ships with it
4 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.
- yesterday First seen · 58 lines · 27 tokens per session scan A 8bdbcc3de695
codexkit-bug-hunt is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 421 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 skills, from other repositories
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
analyzing-security
Scans code for security vulnerabilities, detects dangerous patterns, and ensures security decisions are documented. Use when running security scans, auditing code, or checking for OWASP issues, injection risks, or sensitive data leaks. Automatically triggered on new modules, security-related changes, or post-refactor.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…