Learn Harness Engineering is a project-based course about building the instructions, tools, environment, state, and feedback systems that help AI coding agents work reliably. It is for people learning how to design and understand the surrounding systems that guide coding agents.
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 skills add walkinglabs/learn-harness-engineering --skill harness-creatorgit clone --depth 1 https://github.com/walkinglabs/learn-harness-engineeringWrote 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/walkinglabs/learn-harness-engineering/harness-creator)<a href="https://agentmods.dev/skills/walkinglabs/learn-harness-engineering/harness-creator"><img src="https://agentmods.dev/badge/skills/walkinglabs/learn-harness-engineering/harness-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/walkinglabs/learn-harness-engineering/harness-creator"><img src="https://agentmods.dev/badge/skills/walkinglabs/learn-harness-engineering/harness-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 5.1 | $0.00142 | $0.01115 |
| Opus 5.5 | $0.00057 | $0.00446 |
| Sonnet 5.5 | $0.00028 | $0.00223 |
| Haiku 4.5 | $0.00014 | $0.00112 |
Grade A, and why
harness-creator 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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Creator
Use this skill to make a repository easier for coding agents to start, stay in scope, verify work, and resume across sessions. Keep the harness small enough that agents actually follow it.
Not for model selection, prompt tuning in isolation, chat UI design, or general app architecture.
Core Model
Every useful coding-agent harness has five subsystems:
| Subsystem | Minimal artifact | Purpose |
|---|---|---|
| Instructions | AGENTS.md or CLAUDE.md |
Startup path, working rules, definition of done |
| State | feature_list.json, progress.md |
Current feature, status, evidence, next step |
| Verification | init.sh or documented commands |
Tests/checks the agent must run before claiming done |
| Scope | Feature dependencies and done criteria | Prevents overreach and half-finished work |
| Lifecycle | session-handoff.md, end-of-session routine |
Makes the next session restartable |
First Move
- Inspect what already exists: instruction files, feature/state files, verification commands, docs, package manifests.
- Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether overwriting is allowed.
- Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.
Common Tasks
Create a harness
Use the bundled script when working on a local repository:
node skills/harness-creator/scripts/create-harness.mjs --target /path/to/project
Options:
--agent-file CLAUDE.mdfor Claude-oriented projects.--package-manager npm|pnpm|yarn|bunwhen detection is wrong.--commands "cmd one,cmd two"for custom verification.--forceonly after confirming overwrites are acceptable.
Then explain what was created and how the user should replace placeholder feature entries.
Audit an existing harness
Run:
node skills/harness-creator/scripts/validate-harness.mjs --target /path/to/project
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 290 B
- evals/evals.json 7.1 KB
- metadata.json 1.8 KB
- README-UK.md 3.4 KB
- README.md 2.4 KB
- references/context-engineering-pattern.md 5.1 KB
- references/gotchas.md 6.6 KB
- references/lifecycle-bootstrap-pattern.md 8.1 KB
- references/memory-persistence-pattern.md 4.4 KB
- references/multi-agent-pattern.md 6.3 KB
- references/skill-runtime-pattern.md 1.8 KB
- references/tool-registry-pattern.md 6.0 KB
- scripts/create-harness.mjs 2.7 KB runs code
- scripts/lib/harness-utils.mjs 16 KB runs code
- scripts/render-assessment-html.mjs 839 B runs code
- scripts/run-benchmark.mjs 7.1 KB runs code
- scripts/validate-harness.mjs 1.1 KB runs code
- SKILL.md.en 5.1 KB
- SKILL.md.uk 8.1 KB
- templates/agents.md 2.3 KB
- templates/feature-list.json 1.4 KB
- templates/feature-list.schema.json 1.4 KB
- templates/init.sh 2.6 KB runs code
- templates/progress.md 1.0 KB
- templates/session-handoff.md 509 B
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.
- 1mo ago First seen · 112 lines · 142 tokens per session scan A 6b152a8c5191
harness-creator is a skill published in the GitHub repository walkinglabs/learn-harness-engineering (21,032 stars, last pushed yesterday), licensed MIT. It adds 142 tokens to every session and 1,115 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
openloomi-memory
OpenLoomi Memory is the long-lived context layer of OpenLoomi — a tiered, locally-stored knowledge graph that grows on its own from your Connectors, chats, and Screen Capture. Memory is what makes Chat grounded and what Loop reads before it produces a Decision. It is always on your machine (local-first), always…
continual-learn
Persist learning across turns by actively maintaining MENTALMODEL.md in the workspace. Use for iterative coding, debugging, benchmarking, or any feedback-driven task; read and update the file with actual filesystem writes before every response, never just hidden/internal memory.
ima-skill
A general set of instructions for using a personal knowledge base and notes service to store, search, browse, and retrieve information.
knowledge-base
A skill for managing a knowledge base through the openapi/wiki/v1 API. A knowledge base is a searchable collection of files, web pages, notes, and folders.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…