← Back to Skills Marketplace
Execution Harness
by
_silhouette
· GitHub ↗
· v1.1.0
· MIT-0
134
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install execution-harness
Description
Agent 执行可靠性体系的导航入口。当用户询问 agent 为什么停了、怎么防 agent 提前退出、execution harness 是什么、40 个 pattern 有哪些、6 轴架构、hook 怎么配时匹配。不执行具体操作——各子 skill 分别处理。
README (SKILL.md)
Execution Harness — 导航入口
40 patterns x 6 轴，让 Claude Code agent 把活干完。不是框架，不做模型调用——只管 hook 和脚本。
这个 skill 不执行操作。它帮你找到该用哪个子 skill。
你遇到什么问题？
| 问题 | 用哪个 skill | 关键 pattern |
|---|---|---|
| Agent 做了一半就停了 | execution-loop | 1.1 Ralph Stop Hook — 阻止提前退出，5 个安全阀 |
| "应该可以"但没跑测试 | execution-loop | 1.2 Doubt Gate — 检测投机语言，要求验证 |
cargo build 重试 12 次 |
tool-governance | 2.1 Tool Error Escalation — 3 次提示、5 次 block |
rm -rf 毁了未提交代码 |
tool-governance | 2.3 Checkpoint + Rollback — 自动 git stash |
| 压缩后忘了设计决策 | context-memory | 3.1 Handoff Documents — 决策写磁盘 |
| Context 快满了还在读大文件 | context-memory | 3.4 Token Budget — 80%+ 禁止直读 |
| 限速后 tmux 挂死 | error-recovery | 5.1 Rate Limit Recovery — cron 扫描恢复 |
| 5 个 agent 编辑同一文件 | multi-agent | 4.3 File Claim and Lock — 10min TTL 排他锁 |
| 提交了编译不过的代码 | quality-verification | 6.4 Test-Before-Commit — commit 前跑测试 |
6 轴速查
| 轴 | Skill | Pattern 数 | 核心能力 |
|---|---|---|---|
| 1 | execution-loop | 7 | Ralph Stop Hook、Doubt Gate、Drift Re-anchoring |
| 2 | tool-governance | 6 | 错误升级、权限否决、破坏性命令拦截 |
| 3 | context-memory | 8 | Handoff 文档、Compaction 抢救、Token Budget |
| 4 | multi-agent | 6 | Coordinator/Fork/Swarm、文件锁、盲审分离 |
| 5 | error-recovery | 7 | 限速恢复、Crash 恢复、模型降级建议 |
| 6 | quality-verification | 6 | 编辑后 lint、commit 前测试、session 指标 |
最小配置
3 个 hook 解决最常见的 3 个问题：
// ~/.claude/settings.json
{
"hooks": {
"Stop": [{"hooks": [
{"type": "command", "command": "bash execution-loop/scripts/ralph-stop-hook.sh"},
{"type": "command", "command": "bash execution-loop/scripts/doubt-gate.sh"}
]}],
"PreToolUse": [{"hooks": [
{"type": "command", "command": "bash tool-governance/scripts/tool-error-advisor.sh"}
]}],
"PostToolUse": [{"matcher": {"tool_name": "Write|Edit|MultiEdit"}, "hooks": [
{"type": "command", "command": "bash quality-verification/scripts/post-edit-check.sh"}
]}]
}
}
仓库
GitHub: lanyasheng/execution-harness | 90 tests | 依赖：bash、jq、python3、pytest
Usage Guidance
This bundle is a coherent 'execution harness' and primarily operates on local files and hooks. Before installing or enabling the hooks, do the following: 1) Inspect the included bash scripts (scripts/*) to ensure they do only what you expect — pay attention to any 'git', 'rm', or tmux commands and to where files are written (HOME paths). 2) Backup your ~/.claude/settings.json and any repositories the harness might touch. 3) Run the scripts in a sandbox or container (or under a test HOME) to observe behavior. 4) Start by enabling only non-destructive hooks (e.g., read-only token-budget or context-usage) and review outputs before enabling hooks that run git stash, checkpoint/rollback, or send input to tmux. 5) If you run the test suite (pytest) do so in an isolated environment. 6) Only enable hooks if you trust the source or have audited the code; although there are no external endpoints or requested credentials in the metadata, scripts with filesystem and tmux access can still disrupt local workflows if misconfigured.
Capability Analysis
Type: OpenClaw Skill
Name: execution-harness
Version: 1.1.0
The execution-harness skill bundle is a comprehensive framework designed to improve the reliability, safety, and persistence of AI agents. It provides a suite of bash scripts and hooks that implement defensive patterns, such as blocking dangerous shell commands (tool-input-guard.sh), preventing premature agent termination (ralph-stop-hook.sh), and ensuring code quality through automated linting (post-edit-check.sh). The bundle contains no evidence of malicious intent, data exfiltration, or unauthorized persistence; instead, it focuses on providing deterministic execution controls and safety valves that align with its stated purpose of helping agents complete complex tasks safely.
Capability Tags
Capability Assessment
Purpose & Capability
The declared purpose is a 'navigation entry' for execution reliability patterns and explicitly says it 'does not execute operations' itself. The package contains many bash hook scripts and tests and the SKILL.md gives example settings that call those scripts (e.g., bash execution-loop/scripts/ralph-stop-hook.sh). This is explainable (the hub points users to sub-skills and shipped scripts), but there's a mild mismatch between the 'not execute' wording and the fact that the repo includes runnable scripts and example configs that will execute them if the user wires them into ~/.claude/settings.json. Review the scripts before enabling.
Instruction Scope
Runtime instructions and examples direct agents (or operator's config) to run local bash scripts and to read/write session/transcript files under the user's home (e.g., ~/.openclaw/shared-context/sessions, .working-state, ~/.claude/settings.json). The scripts operate on local filesystem artifacts, tmux panes, run linters/tests, and manipulate state (git stash, write handoff files). They do not reference external endpoints or ask for secrets in the metadata, but they do have broad local-file access — expected for this purpose, but something to audit before enabling.
Install Mechanism
No install spec is provided (instruction-only metadata), which minimizes automatic remote code installation. The bundle includes scripts and tests but no automated download-from-untrusted-URL step. The user would need to place/clone these files and add hooks manually or via their agent config; that manual step is the security control point.
Credentials
The skill declares no required environment variables, credentials, or config paths. The included scripts expect runtime-provided variables (e.g., TRANSCRIPT_PATH, NC_SESSION, COMPACTION_EXTRACT_INTERVAL) typical for hooks; they do not request API keys or tokens. No unrelated service credentials are demanded.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges, but the SKILL.md explicitly recommends editing ~/.claude/settings.json to add hooks that will run the shipped scripts. Enabling those hooks gives the scripts persistent operational presence (they'll run on hook events) and lets them write into user home directories (sessions, handoffs, working-state). This is expected for a hooks-based harness, but it increases the blast radius — inspect scripts and back up configs before enabling.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install execution-harness - After installation, invoke the skill by name or use
/execution-harness - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
修复7个脚本bug(含1个CRITICAL死代码)，新增5个测试，总测试数90→95
v2.0.2
v2.0.2: lightweight root SKILL.md (route-only, ~478 tokens), removed obsolete docs
v2.0.1
v2.0.1: cleanup — remove obsolete reports, add 90 tests, rewrite README
v2.0.0
v2: 6-axis restructure (38 patterns, 17 scripts, 10 meta-principles). Distilled from harness-books, claude-reviews-claude, ccunpacked.dev, claude-howto.
Metadata
Frequently Asked Questions
What is Execution Harness?
Agent 执行可靠性体系的导航入口。当用户询问 agent 为什么停了、怎么防 agent 提前退出、execution harness 是什么、40 个 pattern 有哪些、6 轴架构、hook 怎么配时匹配。不执行具体操作——各子 skill 分别处理。 It is an AI Agent Skill for Claude Code / OpenClaw, with 134 downloads so far.
How do I install Execution Harness?
Run "/install execution-harness" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Execution Harness free?
Yes, Execution Harness is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Execution Harness support?
Execution Harness is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Execution Harness?
It is built and maintained by _silhouette (@lanyasheng); the current version is v1.1.0.
More Skills