Error Debugging
Security scan passedTwo debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.

A self-learning skill layer for Claude Code: distills skills from your real sessions, updates them as you work and prunes unused ones.
by tigerless-labs· AI & agentsUnclaimed · Yours? Claim it
4 images
About
AutoHarness is an open-source Claude Code plugin from Tigerless Labs that maintains a skill library for you. It watches your real sessions, distills reusable lessons into native Agent Skills, folds same-scenario skills together instead of piling up near-duplicates, updates them when you correct them, and archives the ones that stop getting used. It only ever touches the skills it wrote itself. What it does - Learns in the background: once a session has done enough work (every 50 tool calls by default), a reflection reads that stretch of the session and proposes new skills or changes to existing ones - /learn distills the session you're in right now, when you've just worked something out and want it kept - Patches and merges instead of duplicating: a correction updates the existing skill, and a periodic curator pass folds narrow skills into broader ones - Opens each session with a grouped index of the skills it wrote, plus a one-line report of what the last run added or rejected - Keeps a skill by whether later sessions actually use it, not by a benchmark score; unused skills are archived (moved aside, never deleted) and can be restored - Logs why each skill was created or changed, with the redacted session excerpt that justified it How it works - Skills land as plain SKILL.md folders in your project's .claude/skills/ or, for techniques that aren't tied to one repo, in ~/.claude/skills/. Its own state lives in .claude/autoharness/. - Reflection runs as a separate background Claude Code session on Haiku, with read-only tools and one staging tool, so it can only propose. A deterministic validator checks each proposal (safety, structure, size, self-authored only) and is the only part that writes. - By default the reflector gets a redacted window of the session plus a short digest of what came before. - It's tunable with AUTOHARNESS_* environment variables: how often it learns and consolidates, a project-only mode, the session-start index, how many skills each layer keeps, and optional desktop or custom notifications. How to install it - It needs Python 3.11 or newer as python3 on your PATH, with no third-party dependencies. - In Claude Code: /plugin marketplace add tigerless-labs/autoharness, then /plugin install autoharness@autoharness, then /reload-plugins. Good to know - It's MIT-licensed, from Tigerless Labs, and built for Claude Code. - Background reflections are extra Claude Code sessions, so they count toward your usage. They run unattended with permission prompts skipped, limited to read tools and the staging tool. - Uninstalling stops it, but the skills it wrote and its state stay on disk until you delete them. Your own skills are never touched.
Once it’s added
“/learn”
“Remember this workaround for next time.”
“Save how we just fixed this as a skill.”
“Distill the lessons from this session.”
Before you add it
Reads only
Your Claude Code sessions (prompts, replies and tool calls), redacted before reflection · The skills it already wrote, to compare before adding one · How often each of its skills gets loaded or read
Makes changes · your agent can ask first
New and updated skills in .claude/skills/ or ~/.claude/skills/ · A ledger entry and evidence excerpt for every change · Archives its own unused skills (moved aside, restorable)
Each with its own page
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Plugins people install alongside AutoHarness.
No reviews yet. Used AutoHarness? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add tigerless-labs/autoharness /plugin install autoharness@autoharness
Scanned and passed · checked 11 h ago
Scanned on every change, and again when our rules improve.
Tell us and a person on the trust team will look at it. Or email [email protected].
Nobody has shared how they use AutoHarness yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
Plugins people install alongside AutoHarness.
Two debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.
ByteDance's local MCP server that lets your agent run any shell command or script on your machine, with your own permissions.
Keeps your agent's plan, findings and progress in markdown files on disk, so long tasks survive /clear, crashes and compaction.