CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

harness-agents

Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent-Native.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/harness-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-crafted, dense body: executable code, a clearly sequenced workflow, explicit guardrails in the Don't section, and lean token usage throughout. The only notable weaknesses are undefined placeholder variables in the main example and unlinked pointers to the Sandbox Adapters and Agent Teams docs.

DimensionReasoningScore

Conciseness

Lean throughout: assumes Claude's competence, explains only project-specific semantics (resumeState opacity, permissionMode mapping), and keeps the rationale to one tight paragraph. The durable-background bullet in 'Code Execution Sandbox' crams lease/retry/polling/dispatch detail into one dense run-on that could be trimmed.

4 / 5

Actionability

Two complete executable TypeScript blocks (register/resolve harness; startAgentHarnessRun with the full option shape) plus concrete preset ids and env vars. Minor gaps: runId/sessionId/ownerEmail are undefined placeholders, and session persistence, background projection, and installPackage are named without usage examples.

4 / 5

Workflow Clarity

'How' gives a clear numbered 4-step sequence (register adapter → start run via run-manager bridge → persist session state in SQL → surface as background agents) with code or named functions at each step, and the 'Don't' section guards the failure modes. Not a 5 because explicit validation/error-recovery loops are absent, though no destructive or batch operations require them.

4 / 5

Progressive Disclosure

Single-file skill with well-organized, clearly headed sections; no bulk reference material is inlined and nothing warrants separate files at this length. Minor gap: 'See the Sandbox Adapters doc' and 'See the Agent Teams doc' name documents without paths or links.

4 / 5

Total

16

/

20

Passed

Description

65%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description names a specific, well-differentiated niche with strong natural trigger keywords (the harness names themselves), but it only states what the skill covers. It lacks any explicit 'when to use' trigger clause and relies on just two generic action verbs, capping completeness and specificity.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to add or run Claude Code, Codex, Cursor, Pi, Mastra, or other ACP-compliant coding agents inside Agent-Native.'

Replace the generic 'Add or use' verbs with concrete actions such as 'Register a harness adapter, start runs through the run-manager bridge, persist native session state, and surface harness runs as background agents.'

Include natural synonym variations users would say — 'coding agent', 'CLI agent', 'integrate Codex/Claude Code' — to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('full agent harness runtimes') and six concrete runtimes (Claude Code, Codex, Pi, Cursor, Mastra, ACP agents), but the only actions are the generic pair 'Add or use' — no distinct concrete capabilities like registering adapters, starting runs, or persisting sessions are stated.

3 / 5

Completeness

Has a clear 'what' (add or use harness runtimes inside Agent-Native) but no 'when': there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Good natural keyword coverage — 'Claude Code', 'Codex', 'Cursor', 'Mastra', 'ACP', 'agent harness' — that users would plausibly say. A few natural terms are missing, e.g. 'coding agent', 'CLI agent', or task-oriented phrases like 'integrate Codex'.

4 / 5

Distinctiveness Conflict Risk

Clear niche — full external harness runtimes integrated into Agent-Native — with distinct triggers via the named harnesses; minimal overlap risk even against adjacent skills like agent delegation, which concerns Agent-Native's own agents rather than external harnesses.

5 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/harness-agents/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.