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 djscheuf/agentic-dev-ecosystem-template --skill code-reviewgit clone --depth 1 https://github.com/djscheuf/agentic-dev-ecosystem-templateWrote 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/djscheuf/agentic-dev-ecosystem-template/code-review)<a href="https://agentmods.dev/skills/djscheuf/agentic-dev-ecosystem-template/code-review"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/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/djscheuf/agentic-dev-ecosystem-template/code-review"><img src="https://agentmods.dev/badge/skills/djscheuf/agentic-dev-ecosystem-template/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 | $0.00074 | $0.01178 |
| Opus 5.5 | $0.00030 | $0.00471 |
| Sonnet 5.5 | $0.00015 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
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 22d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
A value-first review starts from why the change exists, not from syntax. Requirements first, then tests as evidence, then implementation, then refactoring opportunities. The output is a structured YAML review document.
Inputs
- Target: branch, PR, or diff. Default: the current branch against its merge-base with the default branch.
- Requirements location (optional): story, ticket, spec, or doc paths. If not given, Phase 1 finds them.
- Output path: ask the user at invocation. Default to
{slug}.review.yamlin the working directory.
The code may be human- or AI-written. Apply reference/ai-generated-code.md only when it is relevant.
Non-negotiables
- No review without requirements. Identify the story or stories first. If none can be found, ask the user; if none exist, infer requirements from the PR description and commits, and record a
blockingstorycomment about the gap. - Intent before syntax. Understand what the change is for before judging how it is written.
- Skip what machines catch. Do not comment on formatting, spacing, or style that a linter or formatter enforces. Spend attention on design, intent, and future risk.
- Evidence for every comment. Each comment names concrete source locations and an observed gap. Verify a claim by searching before asserting it (for example, do not claim "no end-to-end tests exist" without checking).
- Review the code, not the person. Do no harm, do good: the aim is a better codebase and a better developer.
- Record comments in the order discovered. Assign priority at the end, not while discovering.
Process
| # | Phase | Question it answers | Read before starting |
|---|---|---|---|
| 1 | Scope | What requirements are under review, and what actually changed? | phases/1-scope.md |
| 2 | Story fidelity | Does the change honor the story and its acceptance criteria? | phases/2-story-fidelity.md |
| 3 | Tests | Is there evidence that each acceptance criterion is met and stays met? | phases/3-test-review.md |
| 4 | Implementation and architecture | Does it fit the system, and will it create tomorrow's problems? | phases/4-implementation.md |
| 5 | Refactor and reuse | Looking beyond the diff, what should be reused or refactored? | phases/5-refactor-and-reuse.md |
What ships with it
13 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.
- output/feedback-style.md 3.5 KB
- output/review-template.md 7.9 KB
- phases/1-scope.md 2.4 KB
- phases/2-story-fidelity.md 1.8 KB
- phases/3-test-review.md 2.2 KB
- phases/4-implementation.md 2.5 KB
- phases/5-refactor-and-reuse.md 2.3 KB
- reference/ai-generated-code.md 3.6 KB
- reference/design-principles.md 4.4 KB
- reference/readability-and-trust.md 4.3 KB
- reference/robustness.md 2.7 KB
- reference/smells-and-refactors.md 3.9 KB
- reference/test-quality.md 3.6 KB
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.
- 22d ago First seen · 79 lines · 74 tokens per session scan A 77c5ff7171f5
code-review is a skill published in the GitHub repository djscheuf/agentic-dev-ecosystem-template (12 stars, last pushed 20d ago), licensed MIT. It adds 74 tokens to every session and 1,178 once invoked, about $0.0003 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 2026-10-01.
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"…
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…
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…
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…