document

A procedure for recording difficult engineering knowledge in project documentation for future maintainers.

In plain words
What is it for?
Use it to document non-obvious features, complex debugging results, known pitfalls, attempted solutions, and the sources consulted.
Why use it?
It prevents important explanations about features, bugs, root causes, failed attempts, and technical decisions from being lost.

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/kodingdev/meridian/document
Any agent
npx skills add KodingDev/meridian --skill document
Clone the repo
git clone --depth 1 https://github.com/KodingDev/meridian

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 673 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 $0.00013 $0.00673
Opus 5 $0.00006 $0.00336
Sonnet 5 $0.00003 $0.00135
Haiku 4.5 $0.00001 $0.00067

Measured yesterday against content hash bfce4b3149a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document 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 yesterday.

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.

skills/document/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document

Capture knowledge for humans. Not for AI, not for ceremony — for the person who maintains this code in six months.

When to Use

  • After completing a feature with non-obvious behavior
  • After resolving a complex debugging session
  • When the user asks to document something

What to Document and Where

Feature Documentation

If the project has a docs/ folder, use it. The spec file from brainstorm is a starting point, but it needs rewriting — specs are instructions for an agent, docs are explanations for a person.

Write for someone who will use or maintain this feature. What does it do, how does it work, what should they know.

Debugging Knowledge / Gotchas

When a complex issue is resolved, especially one that took significant investigation:

  • What the problem was and how it manifests
  • Why it happens (root cause)
  • What the fix is and why it works
  • What was already tried and why it didn't work
  • Sources consulted (URLs, GitHub issues, docs pages)

Place this close to the relevant code: inline comments for small gotchas, a dedicated doc for complex ones.

"We Already Tried This" Notes

For complex ongoing work — like replicating engine-specific rendering in WebGL, or fighting a particularly tricky integration — maintain a living doc of approaches tried:

## Approaches Tried
- **Gamma correction swap (sRGB -> linear)** — didn't work because [reason]. See [source].
- **Manual tone mapping curve** — partially worked but [limitation].
- **[What actually worked]** — works because [explanation]. Key insight: [the non-obvious thing].

This prevents future sessions from re-treading the same ground. If the agent's first instinct is "maybe it's the gamma correction" but that was already tried and documented — the doc catches it.

Architecture Decisions

When a non-obvious choice is made, document why. Not a formal ADR — just a brief note:

  • What was decided
  • What the alternatives were
  • Why this one was chosen

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file 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. yesterday First seen · 68 lines · 13 tokens per session scan A bfce4b3149a5

Subscribe to this mod's changes

document is a skill published in the GitHub repository KodingDev/meridian (5 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 673 once invoked, about $0.0001 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.

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