agentleFS
TechTideOhioTechTideOhio/techtide-harness-kit/CLAUDE.md

techtide-harness-kit

CLAUDE.md0 starsChanged 6 months agoApache-2.0View on GitHub

This repository is a curated marketplace for cloud, zero-trust, and compliance-aware AI workflows. - Keep changes scoped and traceable to the task. - Update catalog metadata when adding, moving, or removing cataloged assets. - Run npm run validate before finishing. The pipeline runs seven gates: validate:catalog, validate:aws, manifest:check, validate:allowed-tools, validate:skill-schema, validate:agent-schema, validate:links. Markdownlint and codespell run separately as the Docs Quality workflow (advisory npm run lint:docs). - If skills/** changed intentionally, also refresh catalog/skill-manifest.json with npm run manifest:write. - Every…

The file

We split this CLAUDE.md into the rules it gives an agent

12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Prefer official docs and live evidence over memory.

    line 17
  2. Distinctive:

    Default to least privilege, zero trust, and safe rollback paths.

    line 18
  3. Distinctive:

    Treat broad permissions, destructive automation, and MCP mutation paths as high risk.

    line 20
  4. Distinctive:

    Do not add secrets, credentials, tokens, tenant IDs, or customer data.

    line 21
  5. Distinctive:

    Keep changes scoped and traceable to the task.

    line 25
  6. Distinctive:

    Update catalog metadata when adding, moving, or removing cataloged assets.

    line 26
  7. Very specific:

    Run npm run validate before finishing.

    line 27
  8. Very specific:

    If skills/ changed intentionally, also refresh catalog/skill-manifest.json with npm run manifest:write.

    line 32
  9. Very specific:

    Every SKILL.md must declare an allowed-tools field (least-privilege baseline) and conform to schemas/skill.frontmatter.schema.json.

    line 34
  10. Distinctive:

    Keep portable logic in canonical specs and shared docs.

    line 45
  11. Distinctive:

    Keep harness-specific behavior in the right adapter format.

    line 46
  12. Distinctive:

    Do not invent unsupported metadata fields in executable agent files.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

TechTide Harness Kit

This repository is a curated marketplace for cloud, zero-trust, and compliance-aware AI workflows.

What this repo contains

  • skills/ - reusable workflows for recurring engineering tasks
  • agents/ - expert roles with judgment for review, architecture, and operations
  • rules/ - harness-specific operating guidance
  • mcp/ - MCP references and trust-boundary notes
  • catalog/ - machine-readable indexes
  • schemas/ - metadata contracts
  • docs/ - governance, taxonomy, compatibility, and quality guidance

Operating stance

  • Prefer official docs and live evidence over memory.
  • Default to least privilege, zero trust, and safe rollback paths.
  • Separate verified facts, judgment, assumptions, and unknowns.
  • Treat broad permissions, destructive automation, and MCP mutation paths as high risk.
  • Do not add secrets, credentials, tokens, tenant IDs, or customer data.

When working in this repo

  • Keep changes scoped and traceable to the task.
  • Update catalog metadata when adding, moving, or removing cataloged assets.
  • Run npm run validate before finishing. The pipeline runs seven gates: validate:catalog, validate:aws, manifest:check, validate:allowed-tools, validate:skill-schema, validate:agent-schema, validate:links. Markdownlint and codespell run separately as the Docs Quality workflow (advisory npm run lint:docs).
  • If skills/** changed intentionally, also refresh catalog/skill-manifest.json with npm run manifest:write.
  • Every SKILL.md must declare an allowed-tools field (least-privilege baseline) and conform to schemas/skill.frontmatter.schema.json.
  • For agents that have a 1:1 companion skill, declare it explicitly via companion_skills: [<skill-id>] in the agent's metadata.json rather than relying on the name-stripping convention.

Cross-platform asset rule

This repo supports multiple harnesses without pretending they are identical.

  • Keep portable logic in canonical specs and shared docs.
  • Keep harness-specific behavior in the right adapter format.
  • Do not invent unsupported metadata fields in executable agent files.

Important files

  • README.md - human-facing vision and repository story
  • AGENTS.md - compressed agent-focused repo guidance
  • CONTRIBUTING.md - contributor onboarding and submission path
  • SECURITY.md - vulnerability disclosure policy and SLA
  • CODE_OF_CONDUCT.md - community standards
  • docs/compatibility.md - harness support contract
  • docs/normalized-platform-matrix.md - naming and platform normalization
  • docs/integrations/skills-cli.md - install-path trust matrix
  • schemas/skill.frontmatter.schema.json - required SKILL.md frontmatter contract
  • schemas/agent.schema.json - agent metadata contract (includes companion_skills)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.