# tigerless-labs/autoharness

> A Claude Code plugin that distills skills from your real sessions, merges similar ones, updates those in use, and prunes unused ones. Runs as a Python hook and MCP server with no third-party dependencies.

- Magnitude: 1.2 out of 10 — Cooling
- Stars: 11,126 total · +0 stars measured 2026-10-16, 00:12–23:40 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-06-09 · Last push: 2026-10-15
- GitHub: https://github.com/tigerless-labs/autoharness · Homepage: https://github.com/tigerless-labs/autoharness · Page: https://gitnova.dev/en/r/tigerless-labs/autoharness

## Useful for

- Install the plugin and let it accumulate skills from your working sessions automatically
- Run /learn after solving a task to keep the lesson immediately
- Tune reflection cadence via AUTOHARNESS_REFLECT_EVERY_N to match your workflow

## Why it’s here

- Star-counter measurements on 2026-10-16 (UTC), 00:12–23:40: 11133 → 11126 stars (-7). This is the change over that interval.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 627
- Issues and pull requests: 270
- Watchers: 257
- Average over the last week: 32 per day
- Usual pace: 405 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: 262, 1120, 29, 1138, 596, 37, 45, 37, 34, 60, 13, 5, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-03 4.5, 10-04 3.3, 10-05 3.5, 10-06 3.7, 10-07 5.5, 10-08 3.5, 10-09 5.1, 10-10 4.1, 10-11 2.1, 10-12 2.1, 10-13 2.1, 10-14 2.2, 10-15 2.1, 10-16 1.4

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-16 23:43 UTC, updated every 30 minutes.