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/cookys/autopilot/distillnpx skills add cookys/autopilot --skill distillgit clone --depth 1 https://github.com/cookys/autopilotWrote 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/cookys/autopilot/distill)<a href="https://agentmods.dev/skills/cookys/autopilot/distill"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/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 | $0.00207 | $0.05410 |
| Opus 5 | $0.00103 | $0.02705 |
| Sonnet 5 | $0.00041 | $0.01082 |
| Haiku 4.5 | $0.00021 | $0.00541 |
Grade C, and why
distill scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> **Durability — the pack MUST have a remote.** A single on-disk copy is one `rm -rf` from total loss. How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
distill — your recurring procedures → your personal skills
autopilot ships this distiller (the factory). The skills it produces are yours (the products)
and land in your skill dirs, never in autopilot's repo. Mirrors how CC's run-skill-generator
writes a per-project skill; autopilot only ships the generator.
Where products go — scope-aware routing
- Global →
~/.claude/skills/autopilot-distill-skills/skills/<slug>/SKILL.md— a skills-directory plugin pack (autopilot-distill-skills@skills-dir) that is also a private git repo = your fleet sync unit, namespaced + separate from your hand-authored personal skills. - Project-specific →
<project>/.claude/skills/<slug>/SKILL.md— rides that project's own git.
Routing is decided by the originating project (cwd) of each signal.
Step 1 — Scan (deterministic, no LLM) — incremental by default
# routine run: only sessions new/changed since last distill (remembers a per-session cursor)
node ${CLAUDE_PLUGIN_ROOT}/scripts/distill-scan.js --real-only --new-only
# first ever run, or "show me everything again": drop --new-only for the full cumulative report
node ${CLAUDE_PLUGIN_ROOT}/scripts/distill-scan.js --real-only
Emits frequency atoms in two buckets: ritual candidates (de-noised procedural command
n-grams) and correction candidates (recurring user-friction contexts). Evidence (counts, source
project) is deterministic — never invented. --json for machine output; --top N to widen.
Cursor (--new-only / --incremental). Each session jsonl is scanned whole exactly once;
its per-session atom contribution is cached in ~/.autopilot/distill/scan-state.json keyed by
{size, mtime}. Unchanged (completed) sessions are reused — only new/grown ones are re-read.
Cumulative totals stay identical to a full scan (the ≥N× value gate is unaffected); the cursor
only changes which sessions are re-read and, with --new-only, filters the report to candidates
whose cumulative count rose this run — i.e. "what's newly worth distilling since last time". This
is what makes /distill cheap to re-run: it picks up where it left off instead of re-proposing what
you already triaged. (Deliberately NOT a raw byte-offset — that would split a session's command
sequence across runs and risk a half-written trailing line. See the script header.)
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.
- 5d ago First seen · 269 lines · 207 tokens per session scan C 67ddd31b9fe3
distill is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed yesterday), licensed MIT. It adds 207 tokens to every session and 5,410 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…