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/run-codeplainnpx skills add plainlang/plain-forge --skill run-codeplaingit 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 | $0.00111 | $0.10088 |
| Opus 5 | $0.00056 | $0.05044 |
| Sonnet 5 | $0.00022 | $0.02018 |
| Haiku 4.5 | $0.00011 | $0.01009 |
Grade A, and why
run-codeplain 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 — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Codeplain
Always use the skill load-codeplain-reference to retrieve the full codeplain CLI reference (every flag, path-resolution rules, config.yaml mapping, render banners, exit codes), and the skill load-plain-reference to retrieve the ***plain syntax rules — but only if you haven't done so yet. This skill drives the codeplain CLI, so the CLI reference is required before launching or resuming any render.
What this skill is
A supervisor around a live codeplain render. The renderer itself is the codeplain CLI; this skill does not generate code. It:
- Launches
codeplain <module>.plain(or attaches to an in-flight run). - Watches three signal sources in a tight loop, in priority order:
codeplain.log— the primary signal. Everything the renderer is doing, deciding, retrying, or failing at gets written here. This is the file you stare at.- the generated code outputs under
plain_modules/<module>/andplain_modules/<module>/tests/— a secondary signal, used to corroborate or contradict what the log says. - the process / TUI itself (alive? exited? exit code?) — a tertiary signal, used only to know whether to keep monitoring.
- Surfaces what is happening to the user in plain English, in near-real-time.
- On pathology, stops the renderer (with user approval), hands off to the right edit skill, and resumes from the last completed functionality.
This skill is read-mostly. It does not modify .plain files itself — it delegates to debug-specs, resolve-spec-conflict, break-down-func-spec, add-implementation-requirement, etc. The only files it writes are control files: it may kill a process, and it shells out to codeplain again to resume.
The log is the ground truth. The TUI is opaque to the agent; the filesystem moves slowly and only on completed steps; but codeplain.log updates the moment the renderer takes any action — API call, retry, fix attempt, test run, abort. If the log and the filesystem disagree, trust the log. If the log and the TUI disagree (per the user's description), trust the log.
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 · 484 lines · 111 tokens per session scan A cf062418775d
run-codeplain is a skill published in the GitHub repository plainlang/plain-forge (55 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 10,088 once invoked, about $0.0006 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…