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 siarhei-belavus/agent-public --skill request-refactor-plangit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/request-refactor-plan)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/request-refactor-plan"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/request-refactor-plan/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/siarhei-belavus/agent-public/request-refactor-plan"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/request-refactor-plan.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 | $0.00054 | $0.00627 |
| Opus 5 | $0.00027 | $0.00313 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
request-refactor-plan 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 8d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill is for shaping a refactor request into a concrete, low-risk RFC. Skip steps only when the context is already strong.
-
Ask the user for a detailed description of the problem, why the current design is unsatisfactory, and any candidate solutions they already have in mind.
-
Explore the repo to verify assumptions, understand the current structure, and identify the real seams, dependencies, and likely blast radius.
-
Ask whether they have considered alternative approaches. Present alternatives and tradeoffs where useful.
-
Interview the user thoroughly about implementation constraints, desired end state, rollout concerns, compatibility needs, and migration expectations.
-
Hammer out the exact scope. Clarify what will change, what must not change, and what should be postponed.
-
Check the codebase for test coverage in the affected area. If coverage is weak, ask the user what their testing plan should be and what safety nets are required before refactoring.
-
Break the implementation into a plan of tiny commits. Follow the principle that each step should be small, reviewable, and leave the system in a working state.
-
Write the refactor RFC as markdown in a local
.rfcs/folder. Create the folder if needed. Use a kebab-case filename derived from the refactor name, and return the final file path.
RFC:
Problem Statement
The problem from the developer or maintainer perspective.
Goals
What this refactor should improve.
Non-Goals
What this refactor will intentionally not address.
Proposed Approach
The proposed solution from the developer's perspective.
Commit Plan
A long, detailed implementation plan in plain English, broken into the smallest practical commits. Each commit should leave the codebase in a working state.
Decision Record
Implementation decisions made so far, such as:
- Modules or subsystems likely to be built or modified
- Interface or boundary decisions
- Technical clarifications
- Architectural choices
- Schema changes
- API contracts
- Important interactions or migration rules
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.
- 8d ago First seen · 87 lines · 54 tokens per session scan A b96a2fda3e07
request-refactor-plan is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 627 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 2026-08-31.
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.
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…