Borrowing it
Nothing to install: this file belongs to phantom/phantom-connect-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phantom/phantom-connect-sdk/main/.claude/skills/audit/SKILL.mdgit clone --depth 1 https://github.com/phantom/phantom-connect-sdkWrote 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/phantom/phantom-connect-sdk/audit)<a href="https://agentmods.dev/skills/phantom/phantom-connect-sdk/audit"><img src="https://agentmods.dev/badge/skills/phantom/phantom-connect-sdk/audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/phantom/phantom-connect-sdk/audit"><img src="https://agentmods.dev/badge/skills/phantom/phantom-connect-sdk/audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00856 |
| Opus 5.5 | $0.00000 | $0.00342 |
| Sonnet 5.5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
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 2mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: audit
Perform a structured code quality review of a single package in this monorepo.
Arguments: <package-name> — matches a directory under packages/ (e.g. react-sdk, browser-sdk, auth2). If all or empty, do an architecture-level review instead.
Phase 0 — Check previous audits
Glob audit/*-{package-name}*.md. If a recent audit exists, read it for prior findings, resolved items, and open issues. Treat it as a hypothesis, not ground truth — verify every claim against current code before repeating it.
Phase 1 — Read and understand
Read every source file in packages/{package-name}/src/. Build a map of:
- What the package exports (check
packages/{package-name}/src/index.tsand package.jsonexportsfield) - What it imports from other workspace packages (
@phantom/*) - What external APIs, browser APIs, or runtime globals it talks to
- What events or callbacks it emits/subscribes to
- Any React context providers or hooks it exposes
Environment branch scan: Before moving on, grep the package for process.env.NODE_ENV, import.meta.env, __TEST__, or any test-environment guards in business logic. Any branch on NODE_ENV === 'test' inside non-test files is a red flag — it means tests run different code than production. Flag every hit with file and line number.
Phase 2 — Read the tests
Read all test files (*.test.ts, *.test.tsx, **/__tests__/**/*.ts, **/__tests__/**/*.tsx) in the package. Assess:
- What is tested vs what is not
- Mock quality: are mocks accurate representations of real dependencies?
- Assertion specificity: do tests verify outcomes or just that functions were called?
- Whether tests exercise error paths, edge cases, and not just the happy path
Phase 3 — Assess quality
Rate each dimension Good / Fair / Poor with one specific observation each:
| Dimension | Rating | Specific observation |
|---|---|---|
| Implementation quality | ||
| Error handling | ||
| Type safety | ||
| Unit test coverage | ||
| Integration coverage | ||
| Architectural fit | ||
| Security |
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.
- 2mo ago First seen · 94 lines · 0 tokens per session scan A 2409fa0747f9
audit is a skill published in the GitHub repository phantom/phantom-connect-sdk (165 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 856 tokens. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…