autosearch:experience-compact

autosearch:experience-compact is a skill for Claude Code from 0xmariowu/Autosearch. It costs 69 tokens per session (1,424 once invoked), scanned A, original, MIT.

An experience-maintenance tool that turns repeated patterns from a log file into a short, current reference guide.

In plain words
What is it for?
It helps update per-skill guidance when patterns recur, feedback is given, files grow, or a session ends.
Why use it?
It keeps useful lessons easy for the runtime AI to read while filtering out isolated or outdated successes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autosearch plugin — 55 skills, 1 agent shipped together

Good fit It helps update per-skill guidance when patterns recur, feedback is given, files grow, or a session ends.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xmariowu/autosearch/experience-compact
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 0xmariowu/Autosearch --skill experience-compact
Clone the repo
git clone --depth 1 https://github.com/0xmariowu/Autosearch

Made for: Claude Code.

Or install autosearch, the plugin that ships this one along with the rest of its 55 skills, 1 agent.

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.

agentmods badge for autosearch:experience-compact

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xmariowu/autosearch/experience-compact/github.svg)](https://agentmods.dev/skills/0xmariowu/autosearch/experience-compact)
Your own site
<a href="https://agentmods.dev/skills/0xmariowu/autosearch/experience-compact"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/experience-compact/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.

agentmods 80×15 button for autosearch:experience-compact

Your own site · 80×15
<a href="https://agentmods.dev/skills/0xmariowu/autosearch/experience-compact"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/experience-compact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,424 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00069 $0.01424
Opus 5 $0.00034 $0.00712
Sonnet 5 $0.00014 $0.00285
Haiku 4.5 $0.00007 $0.00142

Measured 10d ago against content hash be5d11ca0fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autosearch:experience-compact 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.

The scan reads SKILL.md. This mod also ships 1 executable file (__init__.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

autosearch/skills/meta/experience-compact/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

experience-compact — Per-Skill Digest Updater

Reads a skill's experience/patterns.jsonl + existing experience.md, promotes recurring patterns to the digest, prunes stale rules, and rotates raw events if the file is getting large.

Trigger Conditions

Run compact when ANY of:

  1. ≥10 new events added to patterns.jsonl since last compact.
  2. patterns.jsonl > 64 KB.
  3. Last event carried explicit user feedback (user_feedback: accepted or rejected).
  4. Session ending and this skill was used at least once during the session.

Runtime AI (or a cron on long-running instances) calls this skill per trigger.

Promotion Rules

A candidate rule is extracted from patterns.jsonl when the same winning_pattern string or good_query template recurs. To promote it into the Active Rules section of experience.md:

  • seen >= 3 (appeared in at least 3 distinct events)
  • success >= 2 (at least 2 of those events have outcome: success)
  • last_verified <= 30 days (most recent appearance within the last 30 days)

Each promoted rule carries a metadata footer:

seen=5, success=4, last_verified=2026-04-21

Anti-Pollution Rules

  • Single success never promotes. Even if an event looks great, one instance is noise — requires 3 occurrences.
  • User-rejected / rubric-failed / low-relevance events go only into Failure Modes, never Active Rules.
  • User corrections (explicit "no, that's wrong") always promote to Failure Modes with high weight.
  • Cold rules expire. Any Active Rule with last_verified > 30 days moves to a "pending revalidation" bucket; if not re-verified in another 30 days, removed entirely.

experience.md Template

# <skill-name> experience

## Active Rules        # ≤ 20 entries
- <rule> — seen=5, success=4, last_verified=2026-04-21
- <rule> — seen=3, success=3, last_verified=2026-04-19

## Failure Modes       # ≤ 15 entries
- <failure pattern> — seen=4, last_verified=2026-04-20
- <user correction> — seen=1, last_verified=2026-04-18

## Good Query Patterns # ≤ 20 templates
- `{brand} {feature} 翻车 {year}` — seen=7
- `{category} 避雷 小红书 最近` — seen=5

## Last Compacted
- 2026-04-22, from 37 events, promoted 3 rules, archived raw events before 2026-03-22.

Read the full file on GitHub · 132 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. 10d ago First seen · 132 lines · 69 tokens per session scan A be5d11ca0fb2

Subscribe to this mod's changes

autosearch:experience-compact is a skill published in the GitHub repository 0xmariowu/Autosearch (43 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,424 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.

Related

Other skills, from other repositories

memem-mine

Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.

TT-Wang/memem · 26 tokens

hypothesis-tracking

Retrieve and update company hypotheses in Primr. Use when the user asks what is already known, wants to validate a claim, or wants to persist a research finding.

blisspixel/primr · 38 tokens

stats

Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.

kalinbogatzevski/captain-memo · 36 tokens

observations

List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.

kalinbogatzevski/captain-memo · 34 tokens

claude-bridge-role-memory-keeper

Playbook for a Claude Code agent in the dedicated memory keeper role — single-writer for shared agent memory across a team of 3+ peers. Use when you are designated as the keeper (= other peers send you write candidates, you write them and watch for drift). Memory hygiene + reconciliation against the canon + drift…

michalekz/claude-bridge · 102 tokens

recall

Use find before WebSearch or WebFetch for research, or before answering a why/how/what-did-we-decide question. Quarry indexes this codebase, design docs, prior session transcripts, and previously fetched web pages — it often already has the answer. Prefer grep for symbol and value lookups; prefer find for meaning.…

punt-labs/quarry · 155 tokens