load-plain-reference

A reference guide for writing and working with .plain specification files. It covers their structure, concepts, modules, integrations, rendering, testing, and the Codeplain command-line tool.

In plain words
What is it for?
Use it when authoring, editing, reviewing, or debugging .plain files, including checking the installed plain-forge version and loading only the relevant authoring rules.
Why use it?
It helps you follow the rules that the renderer expects and avoid mistakes caused by outdated or misplaced specification details.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/plainlang/plain-forge/load-plain-reference
Any agent
npx skills add plainlang/plain-forge --skill load-plain-reference
Clone the repo
git clone --depth 1 https://github.com/plainlang/plain-forge

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.00997
Opus 5 $0.00037 $0.00498
Sonnet 5 $0.00015 $0.00199
Haiku 4.5 $0.00007 $0.00100

Measured 2d ago against content hash c5ebad2c6cfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

load-plain-reference 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.

forge/skills/load-plain-reference/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load the ***plain reference

Load only the rules and references required for the current task. Files under ../../rules/ are the source of truth for .plain syntax and authoring constraints. Do not restate or override them.

First, confirm the rules about to be loaded are current. On the first invocation of this skill in a session, invoke check-forge-version before loading any rule file. A stale plain-forge ships stale rules, so every routing decision below inherits its verdict.

If that skill reports a stale or unconfirmed install, tell the user clearly that authoring on an outdated plain-forge is not recommended and ask them to run npx plain-forge update before continuing — the rules routed to below may not match what the current codeplain renderer expects. Give them the choice rather than blocking: if they decline, continue with the rules on disk and treat the stale install as the first suspect for anything that later behaves unexpectedly.

Skip the check on later invocations in the same session, and skip it when the network is unavailable.

1. Account for rules already loaded

  • In Claude Code, applicable .claude/rules/*.md files are loaded natively. Do not read those rule files again.
  • In another agent, do not reread a rule whose full content is already present in the current context.
  • Otherwise, read the applicable files from the routing table below before inspecting or changing .plain content.

2. Load applicable authoring rules

All paths are relative to this SKILL.md.

Task or content Rule files
New module, file skeleton, section placement, or comments ../../rules/module-structure.md
Moving facts between sections (see resolve-section-ownership) ../../rules/module-structure.md, plus the rule file of each section involved
Definitions or concept usage ../../rules/definitions.md
Functional specs or acceptance tests ../../rules/func-specs.md
Implementation requirements or unit tests ../../rules/impl-reqs.md
Test requirements or conformance tests ../../rules/test-reqs.md
import modules ../../rules/import-modules.md
requires modules ../../rules/requires-modules.md
required_concepts ../../rules/required-concepts.md
exported_concepts ../../rules/exported-concepts.md
Linked files or resources/ ../../rules/linked-resources.md
Any .plain text or example ../../rules/bullet-continuation.md, ../../rules/concise-specs.md
Drafting or trimming spec wording, or reviewing a spec for verbosity ../../rules/concise-specs-examples.md

Read the full file on GitHub · 90 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 90 lines · 75 tokens per session scan A c5ebad2c6cfe

Subscribe to this mod's changes

load-plain-reference is a skill published in the GitHub repository plainlang/plain-forge (55 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 997 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens