Better Harness is an open-source platform for studying and improving how coding agents work on tasks, using written harnesses, controlled tests, and evidence from projects and sessions. Coding teams use it to identify workflow problems and turn them into prioritized improvements and verifiable next steps. Its catalogue entries extend coding-agent workflows for supported hosts such as Claude Code, Codex, Cursor, and others.
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/qoderai/better-harness/harness-skill-creatornpx skills add QoderAI/better-harness --skill harness-skill-creatorgit clone --depth 1 https://github.com/QoderAI/better-harnessWrote 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/qoderai/better-harness/harness-skill-creator)<a href="https://agentmods.dev/skills/qoderai/better-harness/harness-skill-creator"><img src="https://agentmods.dev/badge/skills/qoderai/better-harness/harness-skill-creator.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 5.1 | $0.00077 | $0.00740 |
| Opus 5 | $0.00039 | $0.00370 |
| Sonnet 5 | $0.00015 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
harness-skill-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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Skill Creator
Create the smallest skill that makes another agent repeat one harness job with evidence, validation, and clear ownership.
Workflow
- Resolve source, target, and host: canonical
skills/<name>/,.agents/skills/wrapper, or both. - Inspect the source chain before designing: entry
SKILL.md, first-hop references, scripts, validators, templates, specs, tests, plugin manifests, and any real smoke evidence. - Load
references/bootstrap-patterns.mdafter the first inventory. Use it to extract patterns, not product-specific rules. - Draft the minimum viable skill map:
- skill name and trigger sentence
- one job the skill owns
- files to create under
skills/<skill-name>/, usuallySKILL.mdplus one reference - evidence boundary and validation commands
- forward-test prompt and pass/fail gates
- Initialize new canonical skills with the system
skill-creatorhelper when available. Addscripts/only for stable repeated automation; keep ad-hoc evaluation prompts out of runtime scripts. - Write the
SKILL.mdas a router. Put trigger conditions in frontmatterdescription, keep the body short, and route detailed rules to first-hop references. - Validate locally, then forward-test. Treat qodercli output as model evidence; local validators and file inspection decide pass/fail.
Design Gates
- Prefer one skill over a stage tree until the target process proves multiple reusable stages.
- Copy ownership shape, not product names, branch policy, private commands, or source-specific team routing.
- Keep
.agents/skills/as a wrapper or mirror when the workflow is shared by the plugin; canonical judgment belongs under rootskills/. - Do not add install, network, server, migration, or dependency-changing commands unless the user requested them and source evidence supports them.
- Prefer portable Node/Python validators or target-owned commands. Do not default generated validation gates to Unix-only
grep/findchecks. - In attachment-only or no-tools forward-tests, never emit tool-call markup, shell probes, or inspection plans; return the skill map with
status: "insufficient-evidence"when needed. - Forward-test
filesis a string array ofskills/<skill-name>/...paths, not objects. - If the generated skill cannot pass
quick_validate.py <skill-dir>, do not describe it as usable. - After any forward-test, verify git status or file inventory for every repo the model was allowed to read or write.
What ships with it
1 file 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.
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.
- 6d ago First seen · 64 lines · 77 tokens per session scan A 2a419ab35cf7
harness-skill-creator is a skill published in the GitHub repository QoderAI/better-harness (2,168 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 740 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
capability-recommender
Use when the need is read-only capability design only: skills, hooks, MCP servers, subagents, plugins, scripts, or CI/headless automation. For cross-surface workbench bootstrap or repair, use harness-builder.
agent-instructions-maintainer
Use when durable agent instructions need audit or repair only: AGENTS.md, CLAUDE.md, .claude.md, .claude.local.md, canonical rules/.mdc, or Cursor rule mirrors. For cross-surface workbench bootstrap or repair, use harness-builder.
implement
用于在一个 scoped active slice 上做最小代码或文档改动。触发条件：用户请求/Spec/Executable Plan 已清楚，工作面和验证路径足够明确。不要在需求、active slice、根因或工作面不清时使用；局部检查只是反馈，ready 只能交给 verify。.
plan
用于把已批准 Spec 或足够明确的非平凡请求转成 Executable Plan。触发条件：需要 active slice、planning surface、验证路径、能力缺口或 commit unit。不要在需求/验证策略不清时使用；先回 brainstorm。项目工作面不清时转 harness-builder。.
diagnose
用于把 build/test/lint/typecheck/CI 或运行时失败诊断成可复现 root cause。触发条件：命令红、行为坏、flaky 或本地/CI 不一致且根因未知。不要在 RED->GREEN 的已知失败或根因已清楚时使用；修复前必须先复现和验证单一假设。.
find-skills
Use this helper to discover reusable agent skills for a clear task or capability gap. Trigger it when the user asks how to do X, find a skill, or extend agent capabilities. Do not install or adopt a skill just because it is related; project adoption belongs to harness-builder.