Borrowing it
Nothing to install: this file belongs to brovar/10x-pentest. 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/brovar/10x-pentest/main/.github/skills/pt-code-review/SKILL.mdgit clone --depth 1 https://github.com/brovar/10x-pentestWrote 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/brovar/10x-pentest/pt-code-review)<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-code-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-code-review/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/brovar/10x-pentest/pt-code-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-code-review.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 | $0.00131 | $0.01700 |
| Opus 5.5 | $0.00052 | $0.00680 |
| Sonnet 5.5 | $0.00026 | $0.00340 |
| Haiku 4.5 | $0.00013 | $0.00170 |
Grade A, and why
pt-code-review 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pt-code-review — Secure Code Review (Stage 3)
Targeted AI/manual secure code review — for each CA-NNN pass, confirm or refute its objective by
tracing data flows source→sink (including cross-repo flows across R-NNN boundaries), and triage
the /pt-code-scan candidates (dropping false positives). Files real issues as one file per
finding (source: code, tier Potential, CVSS-scored, repo-qualified R-NNN/path:line
evidence) per foundation/finding-schema.md, updates its own rows in the test-objectives.md living
ledger, and marks each processed pass reviewed. Static review yields Potential — never verified
(that needs live evidence; the tier-integrity invariant).
When to use, when to skip
- Use to produce evidence-grounded code findings + code-stage coverage.
- Skip the whole code stage if black-box (
repo_access: false) →/pt-dynamic-plan.
Initial Response
- With
<engagement-id>: proceed to Step 0. - Without: print
Usage: /pt-code-review <engagement-id>.and STOP.
Inputs
code/code-plan.md— [blocking] (theCA-NNNpasses + bound methodology; what to confirm).code/review-map.md— [blocking] (theR-NNNregistry + code anchors + cross-repo boundaries).test-objectives.md— [blocking] (thecode/bothrows to resolve; ledger to update).- Source repositories — [blocking].
scope.md— [blocking] (readiness ≠ blocked).- Scan candidates (from
/pt-code-scan, undercode/scan-results/) — [optional] — triage inputs.
Process
Step 0: Validate + resume
Validate scope + inputs. Resume: findings are append-only (F-NNN never reused); ledger + pass-status
writes are idempotent; do not re-triage already-filed candidates. Never reset the ledger.
Step 1: Confirm/refute per pass + triage
For each scanned CA-NNN (and its code/both TM-NNN): trace source→sink — including
cross-repo where the pass is cross-repo-flow — and confirm or refute it. Triage the scan
candidates against the code: confirm real issues, drop false positives (record why).
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.
- 1mo ago First seen · 112 lines · 0 tokens per session scan A 9a5492c62a44
pt-code-review is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 1,700 once invoked, about $0.0005 per session on Opus 5.5. 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 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"…
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…
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…
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…