harness-governance
Governs the Robota harness by checking rule-skill-owner consistency, finding undefined terminology, spotting examples that violate rules, and preferring mechanical checks over duplicated prose. Use when editing AGENTS, skills, or repository guidance.
Best use case
harness-governance is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Governs the Robota harness by checking rule-skill-owner consistency, finding undefined terminology, spotting examples that violate rules, and preferring mechanical checks over duplicated prose. Use when editing AGENTS, skills, or repository guidance.
Teams using harness-governance should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/harness-governance/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How harness-governance Compares
| Feature / Agent | harness-governance | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Governs the Robota harness by checking rule-skill-owner consistency, finding undefined terminology, spotting examples that violate rules, and preferring mechanical checks over duplicated prose. Use when editing AGENTS, skills, or repository guidance.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Harness Governance
## Rule Anchor
- `AGENTS.md` > "Rules and Skills Boundary"
- `AGENTS.md` > "Owner Knowledge Policy"
- `AGENTS.md` > "Harness Direction"
## Use This Skill When
- Editing `AGENTS.md`.
- Adding, removing, or revising skills under `.agents/skills/`.
- Changing owner documents, ADRs, or guidance that other skills depend on.
- Reviewing documentation drift or policy contradictions.
## Preconditions
- Identify the changed rule, skill, or owner files.
- Identify the `AGENTS.md` sections a skill or owner document depends on.
- Identify whether the change should become a mechanical check instead of more prose.
## Execution Steps
1. Map each changed skill to its `AGENTS.md` anchors.
2. Check that every anchor points to a real `AGENTS.md` section.
3. Scan for undefined rule-level terminology introduced only in a skill.
4. Scan for examples that teach forbidden patterns:
- unchecked casts for external data
- implicit fallback logic
- hierarchy-implying agent naming
- blanket dynamic import guidance that contradicts repository policy
5. Remove duplicated policy text when the rule already exists in `AGENTS.md`.
6. If the invariant is important and repeated, propose or add a mechanical scan instead of expanding prose.
7. Summarize:
- anchor validity
- contradictions found
- rule-violating examples found
- candidate checks to automate
## Stop Conditions
- A skill anchor points to a missing `AGENTS.md` section.
- A skill introduces new rule-level terminology without an owner definition.
- A skill example violates repository rules.
- The same policy is duplicated in multiple places with different wording.
## Checklist
- [ ] Changed skills point to real `AGENTS.md` anchors.
- [ ] No new undefined rule terminology is introduced.
- [ ] Examples do not violate repository rules.
- [ ] Duplicated policy prose is reduced where possible.
- [ ] Repeated invariants are considered for automation.
## Focused Examples
```bash
rg -n '^## ' AGENTS.md
rg -n "main agent|sub-agent|parent-agent|child-agent" .agents/skills AGENTS.md
rg -n "fallback to|temporary workaround|Path-Only" .agents/skills AGENTS.md
```
```bash
rg -n "as any|as unknown as|obj as " .agents/skills
rg -n "await import\\(" .agents/skills AGENTS.md
```
## Anti-Patterns
- Treating skills as a second rulebook.
- Leaving stale anchors after renaming `AGENTS.md` sections.
- Adding more prose when a simple scan would enforce the invariant better.
- Keeping examples that contradict the written rule because they are "just illustrative".
## Related Harness Commands
- Current: `pnpm harness:scan`, `pnpm harness:scan:consistency`, `pnpm harness:scan:specs`, `rg`-based consistency scansRelated Skills
scenario-verification-harness
Applies the Robota scenario verification loop by checking scope, preserving canonical ownership, re-recording only when necessary, and stopping on strict-policy failures. Use when scenario files, example flows, or execution-path behavior changes.
pre-refactor-test-harness
Before modularizing or refactoring a package, analyze the code for extraction points, write characterization tests for current behavior, then modularize under test protection. Use when a package has monolithic files that need to be broken into testable modules.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
vitest-testing-strategy
Defines a practical testing strategy for TypeScript and JavaScript using Vitest across unit, integration, and type-level tests. Use when adding features, refactoring, or preventing regressions with fast feedback loops.
version-management
All packages must have the same version. Use changesets for coordinated version bumps. Never version packages independently.
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
user-request-gate
Use immediately when the user requests any implementation, code change, feature addition, fix, or modification. Gates code writing behind a backlog draft document. Read-only exploration is always permitted.
type-boundary-and-ssot
Applies Robota's preferred workflow for trust-boundary validation, strict typing, quality gates, and owner-based SSOT reuse. Use when adding or reviewing type contracts, boundary parsing, shared contract ownership, or running quality checks.
tdd-red-green-refactor
Kent Beck's TDD workflow. Use when writing new code or modifying existing behavior. Enforces the Red-Green-Refactor cycle with small, verifiable steps.
task-tracking
Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.