Long Running Harness

Operating procedure for agent work that spans many context windows: split the run into a one-time initializer session (init.sh, feature_list.json, claude-progress.txt, initial git commit) and repeated coding sessions that each ship exactly one feature, verify it end-to-end via browser automation, and leave the repo in clean committed state. Trigger whenever a build will outlive a single context window (multi-hour/multi-day autonomous coding, session handoffs, resuming a scaffolded project), or when designing a harness/loop for such work.

10 stars 2 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Archive228/lab-skills --skill long-running-harness
Manual install
git clone --depth 1 https://github.com/Archive228/lab-skills.git /tmp/lab-skills
mkdir -p ~/.claude/skills
cp -r /tmp/lab-skills/skills/long-running-harness ~/.claude/skills/long-running-harness

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Long-Running Agent Harness

This skill is the discipline for making progress on a project across many context windows, distilled from Anthropic's engineering post on effective harnesses for long-running agents. Compaction and context management alone are not sufficient: an agent given a high-level prompt (e.g. "build a claude.ai clone") tends to either attempt to one-shot the whole app and exhaust context mid-implementation, or — in a later session — see partial progress and declare the job done. The fix is structural: one initializer session that scaffolds the environment, then many coding sessions that each complete exactly one verified feature and hand off cleanly. Anthropic's framing: "engineers working in shifts, where each new engineer arrives with no memory of what happened on the previous shift."

## When to use

Use this skill when:
- A build or task will span multiple context windows — hours or days of agent work with fresh context each session.
- You are the FIRST session on a greenfield project meant for multi-session work → run the initializer procedure.
- You are resuming a project that already has `init.sh` / `feature_list.json` / `claude-progress.txt` → run the coding-session procedure. Never re-run the initializer on a scaffolded project.
- You are designing a loop/harness that will spawn repeated agent sessions on one codebase.
Read the full skill on GitHub

Details

Skill name
long-running-harness
Path
skills/long-running-harness/SKILL.md
License
MIT
Repo updated
12 August 2026

FAQ

What does the Long Running Harness skill do?

Operating procedure for agent work that spans many context windows: split the run into a one-time initializer session (init.sh, feature_list.json, claude-progress.txt, initial git commit) and repeated coding sessions that each ship exactly one feature, verify it end-to-end via browser automation, and leave the repo in clean committed state. Trigger whenever a build will outlive a single context window (multi-hour/multi-day autonomous coding, session handoffs, resuming a scaffolded project), or when designing a harness/loop for such work.

How do I install the Long Running Harness skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Archive228/lab-skills --skill long-running-harness. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Long Running Harness popular?

It lives in Archive228/lab-skills, which has 10 GitHub stars and 2 forks.

Related skills

Agent Design Fundamentals

10

Archive228/lab-skills

Decision rules for whether to build an LLM agent and how to architect it, distilled from OpenAI's "A Practical Guide to Building Agents": build/no-build criteria, model selection, tool design, single-agent vs multi-agent orchestration (manager pattern vs decentralized handoffs), layered guardrails, and human-in-the-loop triggers. Use when designing, reviewing, or refactoring an agent system — before choosing an architecture, adding more agents, defining tools, or shipping an agent to production without guardrails.

AI, LLMs & Agents

Agent Evals

10

Archive228/lab-skills

Build and maintain evaluation suites for AI agents: bootstrap 20-50 tasks from real failures, pick code-based vs model-based vs human graders by agent architecture (coding, conversational, research, computer-use), write unambiguous tasks with reference solutions, and keep suites alive via ownership and transcript reading. Use when creating evals from zero, adding graders or eval cases, debugging suspicious eval scores, or deciding pass@k vs pass^k metrics for an agent product.

AI, LLMs & Agents

Agent Failure Preflight

10

Archive228/lab-skills

Pre-deployment failure-mode gate for agentic AI systems, distilled from Microsoft AI Red Team's Taxonomy of Failure Modes in Agentic AI Systems v2.0 (grounded in 12 months of red-team engagements). Run it before shipping or materially changing an agent — adding tools/MCP servers/plugins, enabling persistent memory, adding sub-agents or orchestration, enabling computer use, or expanding permissions — to verify concrete controls against memory poisoning, HitL bypass, goal hijacking, supply-chain compromise, session context contamination, capability disclosure, and multi-agent cascade failures.

AI, LLMs & Agents

MCP 2026 Migration

10

Archive228/lab-skills

Migrate MCP servers, gateways, and clients to the 2026-07-28 specification: stateless request-response core (no initialize handshake, no Mcp-Session-Id, version/capabilities in _meta), required Mcp-Method/Mcp-Name headers, Multi Round-Trip Requests replacing server-initiated elicitation/sampling/roots, cacheable list results (ttlMs/cacheScope), CIMD auth over deprecated DCR, the extensions framework (Tasks, Apps, Skills over MCP), and the 12-month deprecation offramp for Roots/Sampling/Logging and HTTP+SSE. Trigger when upgrading any MCP implementation from protocol 2025-11-25 or earlier, writ

AI, LLMs & Agents

Industrial Waste Heat Recovery

5

dungnotnull/industrial-waste-heat-recovery-agent-skill

Industrial Waste-Heat Recovery System Design — Production-grade evidence-backed analysis harness with flexible agent architecture, skill registry, and modular sub-agents. Use for: waste-heat recovery design, heat exchanger selection, ORC systems, pinch analysis, energy efficiency assessment, industrial thermal system optimization. Triggers on: "waste heat", "heat recovery", "ORC", "pinch analysis", "heat exchanger", "energy efficiency", "thermal optimization", "industrial heat", "steam system", "condensate recovery".

AI, LLMs & Agents

MCP Code Execution

10

Archive228/lab-skills

Cut agent token consumption by calling MCP servers through generated code instead of direct tool invocations: present tools as typed wrapper files on a filesystem, discover them progressively, and keep intermediate data in the execution environment (Anthropic measured 150,000 → 2,000 tokens, a 98.7% saving). Trigger when an agent connects to many MCP servers/tools, when tool definitions eat a large share of the context window before work starts, when workflows pipe large intermediate results (transcripts, spreadsheets) between tools, or when sensitive data should not enter model context.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.