What is distill-from-pattern?

A guide for turning repeated actions found in an event stream into one cautious, reusable automated workflow.

Use it to inspect event windows and connector notes, identify the smallest repeated operation, and prepare it for testing and later materialization.

It separates factual event collection from the judgment needed to decide whether a repeated pattern is useful and safe to automate.

distill-from-pattern — Skill for Claude Code by jianzhichun

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.

Any agent

npx skills add jianzhichun/emerge --skill distill-from-pattern

Clone the repo

git clone --depth 1 https://github.com/jianzhichun/emerge

Made for: Claude Code.

Or install emerge, the plugin that ships this one along with the rest of its 15 skills, 10 commands, 3 agents, 24 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jianzhichun/emerge/distill-from-pattern/github.svg)](https://agentmods.dev/skills/jianzhichun/emerge/distill-from-pattern)

Your own site

<a href="https://agentmods.dev/skills/jianzhichun/emerge/distill-from-pattern"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/distill-from-pattern/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jianzhichun/emerge/distill-from-pattern"><img src="https://agentmods.dev/badge/skills/jianzhichun/emerge/distill-from-pattern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 462 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00462
Opus 5	$0.00025	$0.00231
Sonnet 5	$0.00010	$0.00092
Haiku 4.5	$0.00005	$0.00046

Measured 10d ago against content hash 55c2bf763d92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

distill-from-pattern 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 10d 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.

skills/distill-from-pattern/SKILL.md · 35 lines

What it actually says

Distill From Pattern

Use this when pattern_observed, local_pattern_observed, pattern_aggregated, or pattern_pending_synthesis appears in the event stream. The Python layer only emits facts; Claude performs the judgment.

Handoff Contract

scripts/synthesis_events.py is the deterministic packaging boundary. It can append pattern_pending_synthesis and synthesis_job_ready facts for a selected event window, but it does not choose whether the pattern matters, call an LLM provider, smoke-test generated code, or materialize a pipeline.

When the stream only contains pattern_observed, local_pattern_observed, or pattern_aggregated, inspect the facts first. If they justify distillation, package or reference the selected window as synthesis facts, then continue from pattern_pending_synthesis / synthesis_job_ready. Do not reintroduce a Python coordinator.

Workflow

Read the referenced event window from events/events-<profile>.jsonl, events/events-local.jsonl, or events/events.jsonl.
Read connector-local NOTES.md and optional synthesis_hints.yaml.
Infer the smallest repeated operation and choose a generic connector.mode.name intent.
Write conservative exploratory code that assigns __result for reads or __action for writes.
Run one icc_exec with explicit intent_signature and representative args.
If execution fails or verification is ambiguous, report the blocker instead of retrying indefinitely.

Rules

Keep product-specific knowledge in connector-local files, not this skill.
Parameterize only values that vary across event samples.
Prefer a narrow pipeline candidate over a broad one with weak verification.
Never write lifecycle state directly; use the mechanism tools that record WAL and evidence.

Output

Return a concise report with intent signature, source events inspected, icc_exec verification result, and any remaining blocker.

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.

10d ago First seen · 35 lines · 50 tokens per session scan A 55c2bf763d92

Subscribe to this mod's changes

distill-from-pattern is a skill published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 462 once invoked, about $0.0003 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.

Building agents

systematic-debugging

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

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

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…

vercel/next.js · 103 tokens