Borrowing it
Nothing to install: this file belongs to nicograef/handbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nicograef/handbook/main/.claude/skills/distill/SKILL.mdgit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/distill)<a href="https://agentmods.dev/skills/nicograef/handbook/distill"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/distill.svg" alt="Measured on agentmods" 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 | $0.00143 | $0.03736 |
| Opus 5 | $0.00072 | $0.01868 |
| Sonnet 5 | $0.00029 | $0.00747 |
| Haiku 4.5 | $0.00014 | $0.00374 |
Grade A, and why
distill 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 4d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill
Reduce a repository's prose to what a reader cannot get anywhere else. Shape what survives into small files that load cheaply.
- Scope — the whole prose corpus; deletes by default.
- Deletes whole files, whole sections, whole comment blocks.
- Not this skill — sentence-level quality inside a diff or one area: use
/cleanup. /cleanupowns the per-comment rules (../cleanup/code-smells.md)./cleanupowns the prose-slop catalogue (../cleanup/readability.md).- Agent state — sessions, memories, rules: use
/prune.
The method: re-derive, do not edit
- Invert it — suspend the existing structure, decisions and file boundaries.
- Ask the re-derivation question below of each thing.
- Keep is the exception that needs an argument, not the default.
- criteria.md — the bar, what dies, what survives, the hard cases.
- restructure.md — splitting, merging, index design.
- parallelism.md — fan-out design, model routing, the subagent return contract.
If this repository had no documentation, would I write this line from scratch today?
Workflow
1. Scope and safety
Arguments: $ARGUMENTS.
- Paths limit the corpus to those directories or files.
plan-onlypre-answers the mode question in step 5.- Require a clean working tree —
git status --porcelainmust be empty. - Git is the only undo for this skill. Dirty tree: stop and say so.
- Ask nothing yet — the step-5 questions are worth far more grounded in real files.
- Asking twice wastes the user's attention.
2. Inventory
Enumerate the corpus and record the baseline you will be measured against:
git ls-files '*.md' '*.mdx' '*.rst' '*.txt' | xargs wc -l | sort -rn
- Add comment-heavy sources and configs in scope.
- Record per file — path, line count, the one-line question it answers.
- A purpose you cannot state in one line is a finding — that file is several files or none.
- Sum the lines — that total is the before-number in the final report.
- The file count selects the execution mode — inline, parallel subagents, or a
Workflow. - Per parallelism.md — decide here, state it in one line, never re-decide.
What ships with it
3 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.
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.
- 4d ago Changed · -4 lines 010694a7220c
- 8d ago First seen · 289 lines · 143 tokens per session scan A 98ce19786479
distill is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 5d ago), licensed MIT. It adds 143 tokens to every session and 3,736 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…