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 skills add oscarsterling/clelp-skills --skill source-code-reviewgit clone --depth 1 https://github.com/oscarsterling/clelp-skillsWrote 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/oscarsterling/clelp-skills/source-code-review)<a href="https://agentmods.dev/skills/oscarsterling/clelp-skills/source-code-review"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/source-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/oscarsterling/clelp-skills/source-code-review"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/source-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 | $0.00033 | $0.10103 |
| Opus 5.5 | $0.00013 | $0.04041 |
| Sonnet 5.5 | $0.00007 | $0.02021 |
| Haiku 4.5 | $0.00003 | $0.01010 |
Grade A, and why
source-code-review scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
3. **Command injection:** `grep -rlE "child_process|execa|shelljs|[\"']?shell[\"']?[[:space:]]*:[[:space:]]*true|(^|[^[:alnum:]_.])(exec|execSync|spawn|spawnSync|execFile|execFileSync)[[:space:]]*\(" . --exclude-dir=node How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source code review
A manual procedure for reading an application's source the way an attacker would: generate candidate entry points, reconcile them against routing and backend configuration, check each one against a fixed set of questions, and write down why each candidate is or is not a problem. The examples use Next.js App Router, plain Node serverless functions, and Postgres or Supabase. The method carries to other stacks; the grep patterns do not, so rewrite them for yours.
Attribution. This procedure was written after reading deepsec (https://github.com/vercel-labs/deepsec, Apache License 2.0, commit 4fa6722). It is independently written, informed by reading deepsec: the steps, checks, wording, examples and severity rules are our own, and no deepsec source, prompt text, matcher or regular expression is reproduced here. The idea of a census before review, a bypass checklist, and requiring a reason for every dismissal came from reading that project. deepsec's NOTICE file reads, quoted unchanged:
deepsec Copyright 2026 Vercel, Inc. and contributors
This product includes software developed at Vercel, Inc. (https://vercel.com/).
deepsec is not affiliated with this skill and has not reviewed or endorsed it.
What this does and does not cover
It reviews candidate HTTP entry points and their reachable code, direct client access to backend services, and inspected database state. The checks cover authorization, secrets, unsafe output, injection, and the feature-triggered risks below. Record the scope actually inspected.
It does not cover, and a clean report says nothing about:
- dependencies and known CVEs (run your package auditor);
- secrets in git history (run a history-aware secret scanner);
- deployed state not reachable by the read-only catalog queries in step 11: env values, applied migrations, headers, TLS;
- infrastructure as code, CI workflows, containers, mobile apps;
- WebSockets, GraphQL resolvers and tRPC routers beyond the subscription check below;
- client-side DOM code beyond the output checks in step 12.
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.
- 11d ago First seen · 319 lines · 33 tokens per session scan A 2a6d6bfb57a5
source-code-review is a skill published in the GitHub repository oscarsterling/clelp-skills (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 10,103 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
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"…
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…
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…