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 adonai-labs/agent-runway --skill code-reviewgit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/code-review)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/code-review"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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/adonai-labs/agent-runway/code-review"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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 | $0.00092 | $0.03392 |
| Opus 5.5 | $0.00037 | $0.01357 |
| Sonnet 5.5 | $0.00018 | $0.00678 |
| Haiku 4.5 | $0.00009 | $0.00339 |
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 21d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Invoke Command
/review
Files changed: [list of files]
Lens: [all | engineering | security | performance] (optional, defaults to all)
Mode: [compact | isolated] (optional, defaults to compact)
Or when delegated from the lead skill, the file list is passed automatically.
Not sure which skill to use? Start with
/start— it classifies intent and routes to the right skill.
Review Lenses
A complete review examines code through three lenses. Each has a distinct focus and catches a different class of issue.
| Lens | Focus | Where its checklist lives |
|---|---|---|
| Engineering (default) | Clean code, SOLID, architecture, readability, maintainability, error handling | Phase 3 checklists in this skill |
| Security | OWASP Top 10, threat model for sensitive flows, input/auth/crypto/data handling | Security Checklist (OWASP) in reference.md |
| Performance | Algorithmic complexity, N+1 access, resource usage, scalability under load | Phase 3 "Performance & complexity" criterion |
Review modes
Developers choose the review mode based on PR risk and context budget.
Compact mode (default)
Use compact mode for ordinary PRs, small-to-medium diffs, and CI comments where speed and low context usage matter.
- Run one consolidated review over the diff.
- Use
CR,SEC, andSNRas source labels for classification, not as separate loaded workflows. - Keep the prompt and loaded references minimal: core review instructions, relevant stack search/command files, and the output template.
- Do not load deep architecture, security, or contrarian references unless the diff creates a concrete need.
Isolated mode
Use isolated mode for high-risk PRs: security surfaces, auth, PII, audit/compliance, public contracts, data migrations, IaC, concurrency, large cross-layer changes, or changes where the first compact review found serious issues.
- Run focused passes over the same diff with isolated attention:
CR- standard review: correctness, maintainability, DRY, SOLID, Clean Code, and tests.SEC- security review: auth, input validation, data exposure, secrets, injection, dependency, and configuration risk.SNR- senior review: architecture boundaries, operational risk, coupling, API contracts, and long-term maintainability.
- Consolidate the pass outputs into one report.
- De-duplicate by issue, not just by exact line. When two passes flag the same issue, keep one finding, use the highest severity, and list all source labels.
- Report line numbers against the current file, not against diff hunk offsets.
What ships with it
4 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.
- 21d ago Changed · +21 lines 5e63b6c0eb35
- 28d ago Changed · +34 lines 13179f08ff37
- 1mo ago First seen · 280 lines · 92 tokens per session scan A 521526ae99a1
code-review is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 22d ago), licensed MIT. It adds 92 tokens to every session and 3,392 once invoked, about $0.0004 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
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…
full-audit
Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) ->…
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.