Autoharness is a self-learning skill layer for Claude Code that distills skills from real work sessions, combines overlapping skills, updates them during use, and removes ones that are no longer used. It is for people who want Claude Code to maintain a working library of reusable skills as they work. The catalogue entries provide the hooks, agents, MCP integration, plugin, and skill that make up its workflow.
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.
npx agentmods add skills/tigerless-labs/autoharness/learnnpx skills add tigerless-labs/autoharness --skill learngit clone --depth 1 https://github.com/tigerless-labs/autoharnessWrote 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.
[](https://agentmods.dev/skills/tigerless-labs/autoharness/learn)<a href="https://agentmods.dev/skills/tigerless-labs/autoharness/learn"><img src="https://agentmods.dev/badge/skills/tigerless-labs/autoharness/learn.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.00243 |
| Opus 5 | $0.00008 | $0.00121 |
| Sonnet 5 | $0.00003 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
learn 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 yesterday.
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.
What it actually says
Learn: distill this session into the skill library
Review the conversation so far and distill what is worth keeping — through the standard proposal chain, never by writing files.
- Identify class-level, reusable lessons: corrected approaches, non-trivial techniques, durable user preferences. Skip one-off narratives and environment-specific failures.
- Compare first: read the injected skill index; if an existing skill covers
the topic, prefer a
patch/updateover creating a near-duplicate. - Reconcile old with new: when a lesson supersedes an earlier rule, search the managed skill trees for contradicting statements and stage updates so the new version wins everywhere.
- Stage every change exclusively via the
stage_skilltool, one intent per lesson, withreasonand a verbatimevidencequote from this session. The deterministic promoter validates and lands; rejects are reported at the next session start.
If nothing meets the bar, say so and stage nothing.
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.
- yesterday First seen · 25 lines · 16 tokens per session scan A 17f305bff0c9
learn is a skill published in the GitHub repository tigerless-labs/autoharness (1,532 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 243 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
python-best-practices
Python coding best practices. Use when writing or reviewing Python code. Covers type hints, error handling, and common patterns.
connect-required-verification-information
Use this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required…
connect-recommend
Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue…
stripe-apps
Use when building, modifying, or reviewing a Stripe App — or when the user describes something that implies one (e.g. "add a panel to the customer page", "customize my Stripe Dashboard", "react to Stripe events from my app", "connect my service to Stripe without sharing API keys"). Covers the full app development…
stripe-directory
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…
stripe-projects
Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set…