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.
git clone --depth 1 https://github.com/hahaxiang27/FlowHarnessWrote 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/commands/hahaxiang27/flowharness/harness.fix)<a href="https://agentmods.dev/commands/hahaxiang27/flowharness/harness.fix"><img src="https://agentmods.dev/badge/commands/hahaxiang27/flowharness/harness.fix.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 | $0.00026 | $0.00694 |
| Opus 5 | $0.00013 | $0.00347 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
harness-fix 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 7d 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.
What it actually says
Harness 定向修正（Corrector）
上下文管理: ✅ 保持当前上下文（紧跟 /harness.eval 的 FAIL 结果执行）
指令
对 Evaluator 验证失败的项目进行最小化定向修正。
输入参数
$ARGUMENTS — 可选，指定修正轮次或失败项。不指定则自动从上一次 Evaluator 结果获取。
执行步骤
-
获取失败项:
- 如果当前上下文中有 Evaluator 的 FAIL 输出，直接使用
- 否则读取进度文件中最新的失败记录
-
加载修正模板: 读取
.harness/prompts/corrector.md -
执行修正（按 corrector.md 的修正模式）:
- 分析每个失败项的根因
- 确定最小修复范围（哪些文件的哪些行）
- 执行修改
- 不重写无关代码
-
重新验证:
- 重新执行导致 FAIL 的验证级别
- PASS → 更新进度文件，报告修正完成
- FAIL → 检查轮次
- 轮次 < 3 → 继续修正
- 轮次 = 3 → 生成人工介入报告，标记任务为 ⚠️ BLOCKED
-
更新进度文件:
- 记录修正详情到修正记录表
- 更新任务验证状态
修正约束
- 每次修正只改必须改的代码
- 修正不能引入新的编译错误或测试失败
- 修正后必须重新跑 Level 1 验证
- 最多3轮，超过自动升级到人工介入
SDD Step Gate
When specs/{REQUIREMENT_ID}/dashboard-state.json exists (SDD workflow active), after this command completes follow .harness/prompts/command-step-gate.md:
- Update dashboard-state.json and dashboard.html when applicable.
- Mark this command done, next step next, workflow_plan.phase = awaiting_user.
- Stop immediately - do not chain the next internal command in the same turn.
- Hand off with .harness/prompts/step-gate-handoff.md.
Skip only for standalone invocation without dashboard state, or when the user explicitly asks to batch remaining steps.
Requirement Artifact Path Convention
For a requirement id {REQUIREMENT_ID}, keep all delivery artifacts bucketed by that id:
- Specs and dashboards:
specs/{REQUIREMENT_ID}/ - Harness sprint plans/progress:
.harness/sprints/{REQUIREMENT_ID}/ - Harness metrics and reports:
.harness/metrics/{REQUIREMENT_ID}/
Do not create a second numbered feature folder for the same requirement.
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.
- 7d ago First seen · 77 lines · 26 tokens per session scan A 61389a1a35d5
harness-fix is a command published in the GitHub repository hahaxiang27/FlowHarness (4 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 694 once invoked, about $0.0001 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 commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
timeout-fix
A procedure for diagnosing and fixing tests that exceed their time limit by finding causes such as slow processing, hanging network calls, deadlocks, heavy setup, or leaked resources.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…