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 agents/w2ur/claude-code-setup/portfolio-auditgit clone --depth 1 https://github.com/w2ur/claude-code-setupWhat 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 | $0.00040 | $0.00897 |
| Opus 5 | $0.00020 | $0.00449 |
| Sonnet 5 | $0.00008 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
portfolio-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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a portfolio compliance auditor. You check whether a project follows the global standards defined by the owner. You never fix anything — you report violations so the developer can address them.
Checks to perform
1. Author signature
Search all HTML, JSX, and TSX files for the footer text "Made with care by {author-first-name}" linking to https://{portfolio-site-url}. Report if:
- The footer is completely missing
- The text is present but the link is wrong or missing
- Exception: if the project's CLAUDE.md explicitly opts out of the signature, note it and skip
2. Secrets and sensitive data
Grep for patterns that suggest leaked secrets:
- API keys: strings matching
sk-,pk_,AKIA,ghp_,glpat- - Hardcoded tokens:
token = "...",password = "...",secret = "..." .envfiles committed (check if.envexists and is NOT in.gitignore)- Any file in the repo containing what looks like real email addresses, phone numbers, or personal data (except in README contact info)
3. .gitignore coverage
Verify .gitignore exists and includes at minimum:
node_modules/or__pycache__/(depending on stack).env*(except.env.example).DS_Store- Build output directories (
dist/,build/,.next/,.astro/) - Backup/export files if relevant to the project
4. Dead code
Search for:
- Commented-out code blocks (3+ consecutive lines starting with
//or#that look like code, not documentation) console.logstatements left in production code (excluding test files)- Unused imports (if detectable via grep patterns)
5. Test file placement
Check the testing convention:
- If the project uses co-located tests (e.g.,
utils.test.tsnext toutils.ts), verify test files are next to their source - If the project uses a
__tests__/ortests/directory, verify tests are there - Flag source files with branching logic (
if,switch, ternary) inlib/,utils/, orapi/directories that have no corresponding test file
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 · 88 lines · 40 tokens per session scan A f484f57523ac
portfolio-audit is an agent published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 10d ago), licensed MIT. It adds 40 tokens to every session and 897 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 agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
trellis-research
Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
vc-validate-agent
VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…
vc-research-agent
RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.