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.
Borrowing it
Nothing to install: this file belongs to QoderAI/better-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/QoderAI/better-harness/main/AGENTS.mdgit 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/instructions/qoderai/better-harness/agents-md)<a href="https://agentmods.dev/instructions/qoderai/better-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/qoderai/better-harness/agents-md/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/instructions/qoderai/better-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/qoderai/better-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02535 | $0.02535 |
| Opus 5.5 | $0.01014 | $0.01014 |
| Sonnet 5.5 | $0.00507 | $0.00507 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
better-harness AGENTS.md 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Better Harness
Cross-platform support is required (Windows, macOS, Linux). Architecture, directory routing, and template ownership live in docs/ARCHITECTURE.md. Adding support for a new Coding Agent host starts with docs/adapters/contributing-new-coding-agent.md.
UI and Visual Design
- DESIGN.md is the visual source of truth for Harness Studio and interactive Better Harness reports unless a surface owns a narrower approved contract. Read it before changing UI hierarchy, typography, color, density, components, interaction states, or responsive behavior.
- Keep
AGENTS.mdas the routing and enforcement layer; put reusable tokens, visual rationale, component rules, and do/don't guidance inDESIGN.md. - Treat Studio as a VS Code-inspired docked workbench: prefer panes, rows, tabs, toolbars, and editor views over cards, and define pointer and keyboard behavior before adding or changing an interaction.
- Map Studio styles to shared semantic tokens. Do not introduce one-off colors,
font sizes, radii, shadows, an unbundled font family, or broad
!importantoverrides when the design contract already defines the role. - Visual review must prove the primary decision remains obvious at wide, compact, and narrow layouts. Verify keyboard focus, bounded overflow, browser console/page errors, and screenshots for every changed Studio surface.
Plan & Spec
- Write a plan or spec for new agents, hooks, or major features under
docs/specs/<yyyy-mm-dd>-<spec-name>.md, using the spec's creation date. - For non-trivial behavior changes to
skills/,hooks/,scripts/,templates/, adapters, report formats, or review workflows, use.agents/skills/change-traceability-review/SKILL.mdin Spec Preparation mode before implementation. - Prefer
docs/specs/<yyyy-mm-dd>-<story-id>-<slug>.mdwhen there is a Story or issue id; otherwise usedocs/specs/<yyyy-mm-dd>-<slug>.mdfor justified maintenance, docs-only, test-only, dependency, or infra work. - Keep specs reviewable: include intent, acceptance scenarios with stable AC ids, non-goals, plan/tasks, and test/review evidence.
Mark unknowns with
[NEEDS CLARIFICATION: ...]. - Keep
docs/specs/*.mdtitles human-readable. Do not put Story ids, status, or review state in titles, and do not use YAML front matter by default. - Put traceability metadata in the body:
Spec ID, optionalStory, andStatusin a short## Traceabilitysection.
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 · 166 lines · 2,535 tokens per session scan A 42fcab44d451
better-harness AGENTS.md is an instructions file published in the GitHub repository QoderAI/better-harness (2,394 stars, last pushed yesterday), licensed MIT. It adds 2,535 tokens to every session, about $0.0101 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 instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).