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 penwyp/ClaudePreference --skill develop-review-gategit clone --depth 1 https://github.com/penwyp/ClaudePreferenceWrote 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/penwyp/claudepreference/develop-review-gate)<a href="https://agentmods.dev/skills/penwyp/claudepreference/develop-review-gate"><img src="https://agentmods.dev/badge/skills/penwyp/claudepreference/develop-review-gate/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/penwyp/claudepreference/develop-review-gate"><img src="https://agentmods.dev/badge/skills/penwyp/claudepreference/develop-review-gate.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 | $0.00108 | $0.00750 |
| Opus 5.5 | $0.00043 | $0.00300 |
| Sonnet 5.5 | $0.00022 | $0.00150 |
| Haiku 4.5 | $0.00011 | $0.00075 |
Grade A, and why
develop-review-gate 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop Review Gate
Workflow
- Confirm scope and current workspace state.
- Work in the current checkout instead of creating a worktree.
- Inspect the repository and any existing local changes before editing.
- If the worktree is already dirty, preserve unrelated user changes and limit edits to the task scope.
- Implement the requested change in the current checkout.
- Explore the relevant code before editing.
- Finish the feasible scope instead of stopping at a partial patch.
- Keep architecture consistent with the project; do not use temporary patch-style fixes unless the change is truly a local no-risk micro-fix.
- Run self-review pass 1.
- Inspect the diff as a reviewer instead of as the original author.
- Look for correctness bugs, regressions, missing tests, naming issues, leaky abstractions, and unnecessary complexity.
- Apply the fixes that are clearly actionable.
- Run the most relevant tests, lint, or build checks for the changed area.
- Run self-review pass 2.
- Re-inspect the updated diff with the same reviewer mindset.
- Focus on issues left after the first pass: edge cases, maintainability, API consistency, error handling, and test quality.
- Apply the second-pass fixes that materially improve the result.
- Re-run the most relevant verification after the refactor.
- Produce the approval gate output and pause.
- Report the final review findings first. If no blocking findings remain, say that explicitly.
- Summarize what changed, what was refactored during both self-review passes, what verification ran, and what did not run.
- Include the current branch, touched files, and working tree status when relevant.
- Call out residual risks or open questions.
- End in a waiting state such as:
Awaiting human confirmation: continue coding, request more changes, commit, or proceed with the next step. - Do not continue into extra scope, commit, or destructive cleanup unless the human explicitly confirms.
Review Output
Use concise sections in this order:
Self-review findingsChange summaryRefactors appliedVerificationResidual risksAwaiting confirmation
What ships with it
1 file 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.
- 1mo ago First seen · 73 lines · 108 tokens per session scan A 609c5a660df8
develop-review-gate is a skill published in the GitHub repository penwyp/ClaudePreference (136 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 750 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 2026-08-30.
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"…
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…
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…