influencer-discovery
Influencer discovery & contact enrichment pipeline that runs as a Claude Code skill, 15 channels, stdlib only, appends to a Google Sheet.
1 skill219
@tigerless-labsSkill Authoring
Plugin
autoharness
Autoharness, a self-learning skill layer for Claude Code, distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Plugin Signal81/100Strong
maintained100
capable43
documented100
adopted86
Claude Code
> /plugin marketplace add tigerless-labs/autoharness> /plugin install autoharness@autoharness
Codex
$ npx skills add tigerless-labs/autoharness -a codex
Cursor
$ npx skills add tigerless-labs/autoharness -a cursor
Gemini CLI
$ npx skills add tigerless-labs/autoharness -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add tigerless-labs/autoharness$ copilot plugin install autoharness@autoharness
OpenCode
$ npx skills add tigerless-labs/autoharness -a opencode
Windsurf
$ npx skills add tigerless-labs/autoharness -a windsurf
What's inside
2 Agents
curatorPeriodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to disk.reflectorDistill a finished episode into skill changes aligned with the existing library. Compare-first preference, generation stays open; proposes intents only, never writes to disk.
README
With autoharness, we're building the self-learning layer next-gen agents will ship with, learning skills from real work. Today it runs on Claude Code: it learns skills from your real sessions, merges same-scenario ones instead of stacking near-duplicates, updates them in use, and prunes any that stop getting used — so the layer stays clean on its own, touching only the skills it wrote itself.
Same model, different harness — 42% → 78% on CORE-Bench (HAL). The harness does much of the work (swyx's Big Model vs Big Harness), yet it's still rebuilt by hand every model generation. autoharness bets one slice of it — the skill layer — can maintain itself.
| Learns from real work | Each episode is distilled into a skill from the session you were already having — no separate data-collection or replay loop. It fires on its own once a session has done enough work; /learn distills on demand when you want a lesson kept now. |
| Groups, doesn't just pile up | A new episode doesn't always add a skill — the reflector compares it against what's there and folds same-scenario skills into one, so the layer consolidates by category instead of accreting near-duplicates. A fold records which skill absorbed which, so a merge is never mistaken for a death. |
| Keeps its own library in view | Every session opens with a grouped index of the skills it wrote, so recall doesn't depend on the host happening to surface them. The host's native recall is left exactly as it was; the index is added on top. |
| Validated in use, not on a benchmark | A skill survives by being adhered to in later turns (loads over the requests it was available for), not a held-out score. No oracle on the active path, and no tokens spent on a dedicated eval. |
| Only its own skills | Touches only the skills it generated through this plugin — everything else, whether you wrote it or installed it, is left completely alone. |
| Evidence kept for later | Every create/update logs its scenario and decision to a per-skill ledger — the raw material to build a benchmark from real usage if you ever want one. |
Install
Requires Python 3.11+ as the python3 on your PATH — autoharness runs entirely as Python
(zero third-party dependencies); its hooks and MCP server won't fire without it. The hooks resolve
bare python3, so an older interpreter earlier on your PATH (Xcode ships 3.9.6 at
/usr/bin/python3) turns every hook off for the session; autoharness says so on stderr.
Type these in the Claude Code input box.
/plugin marketplace add tigerless-labs/autoharness
/plugin install autoharness@autoharness
Then run /reload-plugins (or restart Claude Code).
Zero config. It now watches your sessions and lands learned skills into .claude/skills/ in the
background. Cadence and lifecycle thresholds are tunable — see Configuration.
Nothing to invoke, but one entry point exists when you want it: /learn distills the session
you're in right now — say it after working something out and the lesson goes through the same
proposal-and-validation chain the background pass uses.
MCP server naming. .claude-plugin/plugin.json registers the server as stage_skill, but agent
definitions reference the fully-qualified name mcp__plugin_autoharness_stage_skill__stage_skill.
This translation is automatic: the plugin runtime constructs the qualified name from the plugin
name (autoharness) and the server key. Outside the plugin context (e.g., registering the server
by hand), the tool would be available as mcp__stage_skill__stage_skill — but the agent allowlists
still reference the plugin-namespaced form. Always install as a plugin to match both names. The
server is declared in the manifest, not in a root .mcp.json, because the plugin root is the repo
root: a .mcp.json there would also be this checkout's project config, which outranks the plugin's
same-command server and leaves the reflector without its tool in sessions inside the repo.
Update
Update and uninstall are shown in their terminal form (claude plugin …); inside Claude Code the same
operations live in the /plugin menu.
Update from a terminal — refresh the catalog by marketplace name, then update the plugin by its
full plugin@marketplace id, then restart:
claude plugin marketplace update autoharness
claude plugin update autoharness@autoharness
Then restart Claude Code to apply — a version bump is a fresh cached copy, not a hot reload.
The refresh is first on purpose: without it, update checks a stale local catalog and may report
already at the latest version when a newer release actually shipped.
Third-party marketplaces have auto-update off by default. To make future releases hands-off,
enable it once: /plugin → Marketplaces → autoharness → Enable auto-update. The
installed copy is cached by the version in plugin.json; a release reaches users only when that
field is bumped.
Uninstall
claude plugin uninstall autoharness@autoharness
claude plugin marketplace remove autoharness
Uninstalling only stops it from running — the skills it landed and its own state live outside the
plugin and stay on disk. To clear those too, delete its state dir (~/.claude/autoharness/ global,
<repo>/.claude/autoharness/ per project) and the self-authored skills under .claude/skills/ (each
carries a self-authored ledger marker, so they're easy to tell from yours). Your own skills are
never touched.
Configuration
Every knob is an AUTOHARNESS_* environment variable with a built-in default — nothing to
configure unless you want to change the pace.
Placement — which layers it manages
| Variable | Default | What it does |
|---|---|---|
AUTOHARNESS_DISABLE_GLOBAL | 0 | Set to 1 for a project-only deployment. Global create intents are rejected before staging and landing; global request/use/view counters, archiving, orphan sweeps, recall, curator snapshots, and metrics are skipped. Existing global skills stay untouched. Project-layer learning continues normally. |
AUTOHARNESS_GLOBAL_ROOT | (unset) | Replaces ~/.claude as the global layer's root. Unset, or set to blank, is stock behaviour — the real home. Set it when autoharness itself has to run sandboxed (a pinned clone, CI, an evaluation harness) and the production skills library must stay untouched. The project layer is unaffected: it is still keyed to the session's own checkout. |
Cadence — when it learns
| Variable | Default | What it does |
|---|---|---|
AUTOHARNESS_REFLECT_EVERY_N | 50 | Reflection cadence, counted in tool calls, not turns: every main-session tool call advances a counter, and the turn that pushes it past N ends with a background reflection. A working stretch triggers; a conversation that only talks never does. Lower = learns faster and spawns more child sessions. |
AUTOHARNESS_CONSOLIDATE_EVERY_N | 250 | Same quantum for the curator, the periodic pass that merges the library as a whole. Held well above the reflection cadence — consolidation is rarer than distillation. |
AUTOHARNESS_DIGEST_EXCHANGES | 20 | How many exchanges before the episode window are compressed into the reflector's prior-context digest (text + tool names only). Unused by the fork carrier, which replays the real conversation instead. |
AUTOHARNESS_CARRIER | bundle | What carries the reflection. bundle hands a redacted window + digest to a fresh subagent. fork resumes and forks the session that just ended, so the reflector reads the real conversation on the parent's warm cache. Stays bundle until the cache-hit measurement is in. |
Recall — what the model sees
| Variable | Default | What it does |
|---|---|---|
AUTOHARNESS_INDEX_SUSPENDED | 0 | Set to 1 to stop injecting the index entirely. Everything else keeps running — the lifecycle pass, the use/view counters, the last-run summary — so this is the switch for measuring what the index is actually worth, and for anyone unwilling to spend the context on it. |
AUTOHARNESS_INDEX_DESC_MAX_CHARS | 60 | Per-line description budget in the session-start index. The index is a scan surface, not the full trigger text — raise it for longer lines, at the cost of context on every session. |
AUTOHARNESS_SKILL_DESC_MAX_CHARS | 1024 | Hard cap on a skill's own description, matching the host's documented limit; a longer one is rejected rather than silently truncated at load. |
AUTOHARNESS_SKILL_BODY_MAX_LINES | 25 | Altitude cap: a SKILL.md body over this many non-blank lines is rejected as a transcript rather than a rule. Backing detail belongs in the skill's references/. |
Lifecycle — what survives
| Variable | Default | What it does |
|---|---|---|
AUTOHARNESS_MATURITY_PROJECT | 100 | Probation gate, project layer: after this many requests have arrived in its layer since a skill landed, it faces graduation review. Until then it's recalled as usual but can't be archived. |
AUTOHARNESS_MATURITY_GLOBAL | 300 | Same gate for the global layer — higher because a global skill loads in every project. |
AUTOHARNESS_CAPACITY_PROJECT | 50 | Cap on mature skills in the project layer. For graduates, capacity contention is the only death: nothing is archived until the mature pool exceeds this, then the lowest usage rates go first. It does not bound the session-start index: probation members are indexed too and are outside this cap, so the index is a function of the creation rate rather than of the two caps. |
AUTOHARNESS_CAPACITY_GLOBAL | 20 | Same cap for the global layer — smaller because its blast radius is every project. |
AUTOHARNESS_GRADUATION_SUSPENDED | 0 | Set to 1 to park graduation review entirely, so nothing is archived for going unused. Meant for when you have reason to doubt the recall surface: archiving on zero use would then be punishing skills for never having been offered. Capacity contention still applies. |
AUTOHARNESS_SNAPSHOT_KEEP | 5 | How many pre-run snapshots of each skill tree the curator keeps before merging. A merge is the one operation a single atomic rename can't undo. |
Notify — hearing about it as it happens
Off by default. The session-start summary line reports a run one session late, with counts but no names; these push the same run account out as soon as a drain finishes. Fail-open: the notifier runs only after the account is written and the intent queue cleared, so a missing, failing or hung notifier can delay a drain but never fail or replay it.
| Variable | Default | What it does |
|---|
Stars on GitHub
Momentum
- stars in total
- 10.9k
File tree
More plugins by @tigerless-labs.
View @tigerless-labs’s profile@tigerless-labsdesign-harness
A decision board for evidence-based design calls, where the human decides and the agent handles the bookkeeping. Sources, ideas and output are kept as plain markdown and shown on a visual canvas, for use with Claude Code and other SKILL.md-compatible agents.
1 skill234
@tigerless-labsSimilar plugins.
See 12 autoharness alternatives
andrej-karpathy-skills
A single CLAUDE.md file of behavioral guidelines for Claude Code, derived from Andrej Karpathy's observations on common LLM coding pitfalls. It helps avoid overcomplicated code, keep changes surgical, and surface assumptions.
1 skill228k
@multica-aigstack
Gives a Claude Code session helpers for product and engineering work: challenging a plan's scope, judging whether an idea is worth building before any code, tracing a bug to its root cause, and reviewing recent work patterns each week.
4 skills138k
@garrytanbook-to-skill
Turns a technical book or a folder of documents into a skill your coding agent can load on demand. It pulls out frameworks, decision rules and anti-patterns, so the agent answers from the real chapter text instead of you pasting the whole book into context.
1 skill38k
@virgiliojr94colleague-skill
Distills colleague, relationship, or celebrity source material such as chat logs and emails into reusable person profiles, and also sets up an owner profile so a personal agent knows who it works for.
1 skill26k
@titanwingsQuestions about autoharness.
Install it with the command on its page. It includes learn. Its skills do not fire on their own yet. Free and open source.
- What is autoharness?
- tigerless-labs/autoharness is a self-learning skill layer for Claude Code that distills skills from your real sessions, updates them as you work, and prunes the ones you stop using. Use it when you want Claude Code to build and maintain its own skills without a separate daemon or benchmark.
- How do I install autoharness?
- Run these in Claude Code: /plugin marketplace add tigerless-labs/autoharness then /plugin install autoharness@autoharness. Then prompt normally.
- Does autoharness auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin.
- Is autoharness free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
- Which coding agents can use autoharness's skills?
- autoharness installs in Claude Code, and its skills also install in Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI. Each skill's page has the install command. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it