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 Stivi7/cyberpunk-context-runners --skill code-reviewgit clone --depth 1 https://github.com/Stivi7/cyberpunk-context-runnersWrote 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/stivi7/cyberpunk-context-runners/code-review)<a href="https://agentmods.dev/skills/stivi7/cyberpunk-context-runners/code-review"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/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/stivi7/cyberpunk-context-runners/code-review"><img src="https://agentmods.dev/badge/skills/stivi7/cyberpunk-context-runners/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 | $0.00024 | $0.00450 |
| Opus 5.5 | $0.00010 | $0.00180 |
| Sonnet 5.5 | $0.00005 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Metadata
- Version: 1.0.0
- Triggers: Worker result ready for Gatekeeper review
- Allowed agents: Gatekeeper
- Side effects: May block integration and request revision
When to Use
Use before every worker merge. Review the actual commit and diff, not only the handoff summary.
Inputs
Work packet, result commit, worker worktree, diff, project context, implementation evidence, baseline failures, and runtime-provided reviewer identity when exposed.
Procedure
- When native delegation is available, start in a fresh context; approval without fresh context is invalid. During parent-session fallback, review independently in the parent and record
review_agent_instance: nullplusreview_context: parent. - Verify result commit, base, scope, and changed files.
- Trace acceptance criteria to implementation and tests.
- Review correctness, boundaries, failure handling, security, compatibility, and maintainability as applicable.
- Rerun relevant verification independently.
- Classify findings as critical, important, or optional with file evidence.
- Approve merge readiness only after required findings are resolved.
- After per-result integration, require a different fresh Gatekeeper instance for assembled review.
Verification
The review identifies the exact commit and includes observed evidence for its decision. Native review uses fresh context. Parent-session fallback records parent context and a null identity; an unavailable runtime-provided identifier is never invented.
Output
review_agent_instance: runtime-provided-id-or-null
review_context: fresh
result_commit: def456
verification_observed: []
verification_skipped_reason: explicit reason when no verification was observed
review_status: approved
An approved per-result review requires a present result_commit and either non-empty verification_observed or an explicit verification_skipped_reason. An approved assembled review requires the same evidence and an integrated_commit.
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 Changed · +13 lines 3dfeebfcb103
- 2mo ago First seen · 39 lines · 24 tokens per session scan A eb67832e479d
code-review is a skill published in the GitHub repository Stivi7/cyberpunk-context-runners (4 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 450 once invoked, about $0.0001 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"…
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…