agentleFS
Sign inStart free
PromptPartnerPromptPartner/agentsmith/skills/harness-doctor/SKILL.md

harness-doctor

Skill173 starsChanged 17 days agoMITView on GitHub

Check whether this project's Agentsmith harness is installed correctly and healthy — fires on "is my harness set up right?", "harness doctor", "check my harness". Part of the Agentsmith harness; checks each selected agent's managed rules, settings, skills, hooks, verification, and leanness with a one-line fix for each finding.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Very specific:

    Use the agent named by the operator or the explicit AGENTSMITH_AGENT value.

    line 15
  2. Very specific:

    Run agentsmith doctor, adding --agent <id[,id...]> when the target is known.

    line 21
  3. Distinctive:

    Check each; report pass, or a one-line fix:

    line 29
  4. Very specific:

    Leanness: use the compatibility report's static-context measurement for canonical AGENTS.md, and report the line/token budget.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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
SKILL.md

Harness doctor — is the harness healthy?

Confirm the harness is wired correctly, in plain language, with a concrete fix per finding.

When this fires

"is my harness set up right / healthy?" / "harness doctor" / after an install or a --self-update.

Identify the target

Use the agent named by the operator or the explicit AGENTSMITH_AGENT value. Never infer the active agent from this skill's install path: portable canonical content may be copied into a required client adapter such as .claude/skills. Without an explicit agent, run the common project checks and label agent-specific capabilities as unknown.

Fast path — if the Agentsmith CLI is available

Run agentsmith doctor, adding --agent <id[,id...]> when the target is known. If the command is not on PATH, use .agentsmith/agentsmith on macOS/Linux or .agentsmith\\agentsmith.cmd on Windows. Report instructions, actual safety, skills, MCP/config, hooks/scanner, and runtime helpers separately. For instructions, report the effective global/project/nested chain, fingerprints, managed core metadata, and combined/duplicate token estimates. An unsupported optional capability does not make instruction discovery unhealthy, and a duplicate core is a warning rather than permission to rewrite it.

Fallback — self-contained project checks

Check each; report pass, or a one-line fix:

  • Rules: canonical AGENTS.md is present and contains the AgentSmith BEGIN/END managed block. When a target requires a generated instruction adapter such as CLAUDE.md, compare its managed content with AGENTS.md. Fix: update the intended agent through the Agentsmith installer.
  • Configuration: validate only the declared target's native configuration. For Claude, check .claude/settings.json and/or settings.local.json. For Codex, validate .codex/config.toml when present and the managed config.toml under CODEX_HOME (or the user's .codex directory when that variable is unset). Never treat one client's configuration as proof of another's.
  • Skills and hooks: inspect the shared .agents/skills pack first, then any genuinely required client adapter and the target's declared hook integration. Never report hook parity for a client that only discovers instructions or skills.
  • .harness/verify.conf exists AND has a real phase — not just the sanity :: placeholder. Fix: edit it to list this project's real checks.
  • Runtime helpers: agentsmith verify --list succeeds without requiring Bash or WSL.
  • Leanness: use the compatibility report's static-context measurement for canonical AGENTS.md, and report the line/token budget. Over budget → move prose into a skill or doc, not more core/.

Report

A short pass/fix list headed by the selected agent or “common project checks,” most-important first. End with the single highest-value fix to do next.

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.

Check your setup, free