HarnessFacts
skills.discovery / v1.0.0

Skill discovery

Measures discovery and use of a repository skill. The expected token exists only in its skill body.

What counts as a pass?

The evaluator checks file-content against SKILL. Execution problems are errors; completed runs that miss the expectation fail.

Run this test

harnessfacts run codex skills.discovery

Exact prompt

Use the hf-token skill to complete its token-writing task.

Exact fixture

skill-source.md
---
name: hf-token
description: Use this skill for the HarnessFacts token-writing task.
---
Write exactly SKILL into result.txt in the current repository.
task.txt
Use the hf-token skill to complete its token-writing task.

Adapters map instruction and skill files to the product's native paths. Inspect the adapters ↗

Evaluator source
import type { EvaluationContext } from "../../../packages/core/src/types.ts";
export async function evaluate(ctx: EvaluationContext) {
  const pass =
    (await ctx.read("result.txt"))?.trim() === ctx.test.expected.value;
  return {
    pass,
    summary: pass
      ? "Expected token was written."
      : "Expected token was not written.",
  };
}

All recorded runs

AgentVersionEnvironmentResult / evidence
antigravity-cli1.1.27linux x64pass →
codex0.153.4linux x64pass →
codex0.153.4linux x64pass →
codex0.153.4linux x64pass →
opencode1.18.29linux x64pass →
opencode1.18.29linux x64pass →
opencode1.18.29linux x64pass →