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 rekabytes/opencode-skills --skill code-reviewgit clone --depth 1 https://github.com/rekabytes/opencode-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/rekabytes/opencode-skills/code-review)<a href="https://agentmods.dev/skills/rekabytes/opencode-skills/code-review"><img src="https://agentmods.dev/badge/skills/rekabytes/opencode-skills/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/rekabytes/opencode-skills/code-review"><img src="https://agentmods.dev/badge/skills/rekabytes/opencode-skills/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 | $0.00009 | $0.01410 |
| Opus 5.5 | $0.00004 | $0.00564 |
| Sonnet 5.5 | $0.00002 | $0.00282 |
| Haiku 4.5 | $0.00001 | $0.00141 |
Grade A, and why
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 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Patterns
1. Code Quality Checks
Naming Conventions
- Variables:
camelCasefor locals,PascalCasefor classes/types - Constants:
SCREAMING_SNAKE_CASEorcamelCasedepending on scope - Files: Match the primary export name
- Boolean variables: Use
is,has,should,canprefixes
Function Quality
- Single responsibility principle
- Max 20-30 lines per function
- Max 3-4 parameters (use object for more)
- Early returns to reduce nesting
- Meaningful function names (describe what, not how)
Code Smells to Detect
| Smell | Detection | Suggestion |
|---|---|---|
| Long function | >30 lines | Break into smaller functions |
| Deep nesting | >3 levels | Extract to helper functions |
| Magic numbers | Unnamed literals | Extract to named constants |
| Duplicate code | Similar blocks | Extract to shared function |
| Dead code | Unused imports/vars | Remove |
| Large files | >300 lines | Consider splitting |
2. Error Handling Patterns
Good Patterns
// Early return with error
function process(data: Data): Result | Error {
if (!data) return new Error('Data required')
if (!data.valid) return new Error('Invalid data')
return processValidData(data)
}
// Result type pattern
type Result<T> = { ok: true; value: T } | { ok: false; error: string }
Anti-Patterns
// Swallowing errors
try { something() } catch (e) { /* silent */ }
// Empty catch blocks
try { risky() } catch (e) {}
// Catching without handling
try { operation() } catch (e) { throw e }
3. Performance Checks
Common Issues
- N+1 queries in loops
- Missing memoization opportunities
- Large bundle imports
- Synchronous operations that could be async
- Unnecessary re-renders (React)
- Missing indexes on queried fields
Red Flags
// In loop - potential N+1
for (const user of users) {
await fetchUserDetails(user.id)
}
// Better
const details = await Promise.all(
users.map(u => fetchUserDetails(u.id))
)
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 · 214 lines · 9 tokens per session scan A 2b3aa416b6b8
code-review is a skill published in the GitHub repository rekabytes/opencode-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 1,410 once invoked, about $0.0000 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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
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…