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 instructions/hilt21/adaptive-harness/agents-mdgit clone --depth 1 https://github.com/hilt21/Adaptive-HarnessWhat 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 | $0.01429 | $0.01429 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
Adaptive-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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件适用于整个仓库。若子目录以后出现更具体的 AGENTS.md,以离目标文件最近的说明为准。
项目定位
Adaptive Harness 是本地优先、客户端无关的渐进式 Agent Harness。首版为 Python 3.12+ 的 CLI 与可嵌入 Runtime,核心目标是提供可信的工作区身份、能力边界、执行证据和完成门禁,而不是替模型增加固定的分析或开发流程。
当前仓库包含 v0.2 Runtime 前身实现和 v0.3 目标设计。阅读或交付时必须区分 implemented、partial 与 planned,不得把目标设计描述为当前能力。
事实来源
不同类型事实由以下文件分别负责:
- 产品目标、范围、不可破坏约束和验收边界:
docs/adaptive-harness-prd.md - 组件边界、依赖方向、权威关系和失败语义:
docs/architecture/ - 机器协议:
src/adaptive_harness/schemas/ - 协议版本和兼容政策:
docs/contracts/ - 重要设计决策及原因:
docs/adr/ - requirement、实现、测试和发布证据映射:
docs/acceptance/traceability.md - 实现顺序:
docs/v0.3-observability-evolution-sprint-plan.md
这些来源按领域分工,不互相覆盖。发现矛盾时停止实现,记录冲突并修正相应事实来源,不得自行选择最宽松解释。
架构边界
- Kernel 不得依赖 Observability、Experience 或 Evolution。
- Observability 和 Experience 是派生层,不得参与 capability、approval 或 completion 判断。
- Evolution 只能协调注册 Manager 执行 mutation,不得成为 canonical config、Capability 或 Completion authority。
- 新增跨领域依赖前必须更新 dependency rules、architecture overview 和相应测试。
planned能力不得在代码、文档或交付报告中描述为implemented。
不可破坏的约束
- 最小内核包含 Task Envelope、Capability Gateway、Executor、Verifier 和 Task Store;这些组件及其安全 invariant 不可关闭或被可选模块削弱。
- 按 capability、真实副作用和环境治理操作,不按任务名称或命令字符串推断安全性。
- 模型声明、自评和模板输出不能作为完成证据;
completed必须由当前任务的合法 acceptance evidence 支持。 - 权限取交集、限制取最严格值、deny 优先。未知字段、未知副作用和越界路径必须拒绝或升级审批。
- required acceptance 不得由模型自动删除;base SHA 在同一任务内不可改变;失败和不利证据不可覆盖。
observe与enforced必须如实标注。无法确认客户端具备拦截能力时使用observe。- 默认本地、离线、零遥测;不得回显 secret,也不得把未经脱敏的数据写入模型上下文或导出物。
- 初始化和配置修改必须先展示 diff、经用户确认后原子应用;失败时恢复原状态。
- Authority 归属与 contract execution 是两项独立职责。每个 canonical owner 必须在 authoritative write/publish 前、canonical read 返回可信数据前执行完整版本化 contract;producer 校验与 integrity digest 都不能替代该边界。
- PRD 中每条验收 requirement 必须有唯一稳定的
F-xxx-Ryy;coveredtraceability 必须引用存在的 pytest node ID和已登记 contract ID。路径存在只证明追踪链完整,不能替代语义 coverage review。
预期结构
实现代码放在 src/adaptive_harness/,按架构控制面中的边界组织:core/、cli/、adapters/、scanners/、modules/、templates/、feedback/ 和 schemas/。测试放在 tests/,测试数据放在 fixtures/,设计与用户文档放在 docs/。
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.
- 2d ago First seen · 86 lines · 1,429 tokens per session scan A 2a15cb564f24
Adaptive-Harness AGENTS.md is an instructions file published in the GitHub repository hilt21/Adaptive-Harness (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,429 tokens to every session, about $0.0071 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 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.