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 agentmods add skills/plainlang/plain-forge/refactor-modulenpx skills add plainlang/plain-forge --skill refactor-modulegit clone --depth 1 https://github.com/plainlang/plain-forgeWhat 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 | $0.00060 | $0.02359 |
| Opus 5 | $0.00030 | $0.01179 |
| Sonnet 5 | $0.00012 | $0.00472 |
| Haiku 4.5 | $0.00006 | $0.00236 |
Grade A, and why
refactor-module 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 2d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Module
Always use the skill load-plain-reference to retrieve the ***plain syntax rules — but only if you haven't done so yet.
When to Use
- A module has many functional specs spanning multiple distinct domains or feature areas.
- The module is hard to reason about because unrelated concerns are interleaved.
- New features are difficult to add because the module's scope is too broad.
- The user explicitly asks to split or reorganize a module.
Guiding Principle
The refactoring is purely structural. The combined behavior of the resulting modules must be identical to the original module. No functional spec is added, removed, or weakened. The split is semantic — grouping related specs together — not behavioral.
Input
The .plain file to refactor, plus guidance from the user on the desired grouping (or ask the user to confirm your proposed grouping).
Phase 1 — Analyze the Current Module
- Read the entire
.plainfile — frontmatter, definitions, implementation reqs, test reqs, and all functional specs. Also read anyimportandrequireschains to understand the full context. - Inventory the functional specs. Number each spec and note which
:Concepts:it references. Build a dependency map: which specs depend on earlier specs (by referencing behavior or state they introduced)? - Inventory the definitions. For each concept, note which functional specs reference it. Identify concepts that are used across multiple logical groups vs. concepts used only within one group.
- Identify logical groups. Look for natural seams — clusters of functional specs that share concepts, represent a cohesive domain, or describe a single feature area. Common groupings:
- Data model setup and CRUD operations
- Business logic and processing rules
- UI screens and navigation
- Integrations and external interfaces
- Statistics, reporting, and analytics
- Verify group independence. Each group's specs should form a contiguous or near-contiguous block in chronological order. If a group's specs are scattered and interleaved with other groups, the split boundary may need adjustment.
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.
- 2d ago First seen · 198 lines · 60 tokens per session scan A b556ea79bbc0
refactor-module is a skill published in the GitHub repository plainlang/plain-forge (55 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 2,359 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…