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/d-padmanabhan/agent-engineering-handbook/codebase-security-auditnpx skills add d-padmanabhan/agent-engineering-handbook --skill codebase-security-auditgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/codebase-security-audit)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/codebase-security-audit"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/codebase-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 | $0.00172 | $0.06181 |
| Opus 5 | $0.00086 | $0.03090 |
| Sonnet 5 | $0.00034 | $0.01236 |
| Haiku 4.5 | $0.00017 | $0.00618 |
Grade A, and why
codebase-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 2d 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 — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Security Audit & Remediation
A systematic, multi-layer security review with actionable fixes. Combines static (SAST), composition (SCA), secrets, data-flow / taint, semantic / CPG, infrastructure (IaC), custom rules, and dynamic (DAST) checks - and wires the results into CI/CD for continuous coverage.
Companion rules:
310-security.mdc- principles + OWASP Top 10 + NHI Top 10316-zero-trust.mdc- Zero Trust principles (always-on)160-github-actions.mdc- secure CI workflow patterns
When to invoke
Use when the user asks to:
- "Security audit" / "harden this repo" / "check for vulnerabilities"
- "Find committed secrets" / "scan for credentials"
- "OWASP audit" / "Top 10 review"
- "SAST scan" / "SCA / dependency audit" / "IaC audit" / "DAST validation"
- "Set up continuous security scanning"
- Open / re-open a security incident triage on a codebase
Tooling Stack - Eight Practical Layers
Map every audit to these eight layers so coverage is explicit and gaps are visible.
| # | Layer | Purpose | Recommended Tools |
|---|---|---|---|
| 1 | Secrets scanning | Find exposed credentials in code & git history (regex + entropy) | gitleaks, trufflehog, detect-secrets, ggshield, ripgrep regex |
| 2 | SAST (static) | Code-level vulns - injection, crypto, access control | semgrep, codeql, bandit (Python), gosec (Go), eslint-plugin-security (JS/TS), spotbugs + find-sec-bugs (Java), brakeman (Ruby), cppcheck / flawfinder (C/C++) |
| 3 | SCA (deps) | Vulnerable / outdated / license-risky packages | pip-audit, safety, npm audit, yarn audit, govulncheck, mvn dependency-check, osv-scanner, grype, trivy fs, Snyk, Dependabot / Renovate |
| 4 | Data-flow / taint | Track untrusted input through code to a dangerous sink | semgrep (mode: taint), CodeQL data-flow libs, Pysa (Python) |
| 5 | Semantic / CPG | Behavior-aware deep analysis - privilege escalation, auth bypass | CodeQL (full DB build), Joern |
| 6 | IaC scanning | Misconfig in Terraform / K8s / cloud / Dockerfiles | checkov, tfsec, terrascan, kube-linter, kubesec, kics, trivy config, hadolint |
| 7 | Custom rules | Business-specific risks the off-the-shelf rules miss | Semgrep custom rules in .semgrep/, CodeQL custom queries in .github/codeql/ |
| 8 | DAST (dynamic) | Validate runtime behavior on the deployed app | OWASP ZAP, Nuclei, Burp Suite, sqlmap (targeted) |
What ships with it
3 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.
- 2d ago First seen · 570 lines · 172 tokens per session scan A 2747c94ba0f5
codebase-security-audit is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 6d ago), licensed MIT. It adds 172 tokens to every session and 6,181 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…