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 humanerd-drew/opencode-drewgent --skill requesting-code-reviewgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/requesting-code-review)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/requesting-code-review"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/requesting-code-review.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 | $0.00021 | $0.07406 |
| Opus 5 | $0.00010 | $0.03703 |
| Sonnet 5 | $0.00004 | $0.01481 |
| Haiku 4.5 | $0.00002 | $0.00741 |
Grade B, and why
requesting-code-review scanned grade B with 2 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 4d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
restarting: `rm -rf .wrangler/state/v3/d1/` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Test before change** — curl key endpoints, confirm baseline 200 How it starts
The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Codebase Audit (Existing Project)
Use this when the user asks you to review an entire project — not a diff of pending changes, but the whole living codebase. You are finding architecture, security, DB, and quality issues in already-deployed code.
Core principle: Read systematically — config first, entry point, then follow imports. Never judge a file without knowing where it fits in the dependency graph.
When to Use
- User says "review this project", "code review", "audit", "architecture review"
- Before starting work on an unfamiliar codebase
- After inheriting a project or acquisition
Core Principles
-
Map the full picture before proposing action. The user knows their system — when they say something works but grep says no, check actual deployed endpoints before declaring it missing. The deployed version may differ from the local code. Ask: "show me / let me check the running site" before concluding something doesn't exist.
-
Root cause before workaround. When a service fails (API timeout, null response), don't propose changing the call order as a fix. First verify the keys/endpoints work independently, then trace the exact call chain to find the real bottleneck. The user will call out cosmetic fixes that don't address the underlying problem.
-
Map the dependency graph first. Read config → entry point → follow imports. Never judge a file without knowing where it fits. Produce a visual reference of import chains, HTML script tags, and CSS @import before proposing changes.
-
Risk-segment every refactoring proposal. Before suggesting structural changes, categorize each by risk level so the user can decide what's safe:
Risk Criteria Examples Zero (0%) Dead code, confirmed no references Orphaned files, never-read config keys Low Verifiable by loading the app CSS dedup, dead config removal Medium Needs careful testing Module splitting, route refactoring High Design-level reconsideration Bundler adoption, framework migration
What ships with it
6 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.
- 4d ago First seen · 656 lines · 21 tokens per session scan B cf7aa618d4cf
requesting-code-review is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 7,406 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
a0-review-plugin
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
laravel-audit
Perform a deep, structured, evidence-based audit of a Laravel application and produce actionable findings backed by concrete project evidence. Use when asked to audit, review, assess, or evaluate an existing Laravel codebase.
laravel-audit-dsa
Run a read-only, orchestrated audit of a Laravel codebase for data structures, state representation, algorithms, and ownership. Use when asked for a DSA audit, subsystem inventory, or Aaron-style bounded agent audit.
代码审查员
A code-review agent that examines changes for correctness, security, maintainability, performance, and test coverage.