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 skills add JHostalek/dotclaude --skill distillgit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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/jhostalek/dotclaude/distill)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/distill"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/distill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/distill"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/distill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00021 | $0.00373 |
| Opus 5.5 | $0.00008 | $0.00149 |
| Sonnet 5.5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
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 9d 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.
What it actually says
Distill
Distill the target (my text, a named file, or else my previous message) into expert-register English. I write in a second language; you hold the vocabulary I lack. Elevate to it.
The reader is a domain expert or a model. A term of art is the established word practitioners use for a concept: it carries a sentence or a paragraph of intent and recruits the reader's priors for free.
- Intent: list every claim, constraint, exclusion, name, and branch in the original. Done when each original sentence maps to an item.
- Distill: name each item with its term of art, then write the shortest text that carries the whole list. Cut restatement, hedging, and explanatory scaffolding. Choose the term practitioners actually use over the rarer synonym: precision, not ornament. Reject a term whose home-domain connotation pulls the wrong way. Keep my names, numbers, and stance.
- Back-translate: give a cold-reader subagent the draft alone and ask it to restate the intent as a list. Diff that against step 1; each missing or drifted item is a loss to fix. Done when the lists match, or two rounds have run. Without subagents, expand each term yourself against step 1.
- Return: the distilled text, then a glossary of each term you introduced and the meaning it replaced, so I learn it. When the target is a file, apply the rewrite there and report the word count before and after.
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.
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.
- 9d ago First seen · 18 lines · 21 tokens per session scan A caebba76338b
distill is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 3d ago), licensed CC0-1.0. It adds 21 tokens to every session and 373 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
pulser
Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter, conflicts, usage-hooks), classifies skill types, generates prescriptions, and runs eval tests. Use when checking skill quality, auditing…
poteto-mode
Bundled skills live at ../ /SKILL.md from this file, so put this file's absolute path in every poteto-agent prompt.
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
create-formal-verification-skill
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers…
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.