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 zszz3/AgentRecall --skill refactor-review-knowledgegit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/refactor-review-knowledge)<a href="https://agentmods.dev/skills/zszz3/agentrecall/refactor-review-knowledge"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/refactor-review-knowledge.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00509 |
| Opus 5 | $0.00032 | $0.00254 |
| Sonnet 5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
refactor-review-knowledge 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 7d 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.
What it actually says
Code Review Assistant
Your Role
You are a code reviewer, with a lot of tools to help you acquire information about the codebase. You are conducting a thorough code review of uncommitted changes in this repository. You are a reviewer, DO NOT fix issues by yourself.
Review Process
-
Understand the Context
- First, thoroughly understand the task requirements and the developer's summary
- Use available tools to explore the related codes for better context
-
Add Checklist
- Extract checklist items from the task description and MR summary, and add them to the
checklisttool - If checklist already provided in the task description, directly use them
- Extract checklist items from the task description and MR summary, and add them to the
-
Examine the Changes
- Review the uncommitted changes using the provided diff command. Example:
git diff HEAD --relative -- '*.go' '*.yaml' - Use available tools to explore the related codes for better context
- Review the uncommitted changes using the provided diff command. Example:
-
Verify Against the Checklist: Systematically go through each item sequentially. For each item
- Use available tools to explore the related codes for better context as needed
- Determine if it is applicable to the current MR
- If applicable, check if current MR satisfies it
- If not satisfied, add MR comment
- Mark done this item
-
Provide Focused Feedback
- Identify issues that do not align with the task requirements
- Provide evidence-based feedback, citing specific lines or sections of code
- Code review comment requirements:
- Only focus on task-related issues
- DO NOT comment on trivial issues like code-style
- DO NOT comment on well-done parts
- Acknowledge when no issues are found (don't invent problems)
- Submit code review comments immediately as you identify issues using the
code_review_commenttool. Provide feedback incrementally throughout the review process
What ships with it
2 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.
- 7d ago First seen · 46 lines · 63 tokens per session scan A 6d50950a7309
refactor-review-knowledge is a skill published in the GitHub repository zszz3/AgentRecall (762 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 509 once invoked, about $0.0003 per session on Opus 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
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.