Index of every page on this site: llms.txt
All skills
minimax-ai avatar

/harness-experiment

@0db1b4f
by MiniMaxminimax-ai/mcode-stack736 stars
50
Run it yourself

Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and looking at flipped tasks, request count, tokens and cache hits, not just the average score. Use before and after changing prompts, tools, skills, subagent layout, compaction or other agent scaffolding, or when asked whether a change helped.

Use this Skill: https://skilld.dev/gh/minimax-ai/mcode-stack/harness-experiment

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈95 tokens for metadata: the name and description. ≈654 when used: this file.

Description uses 4.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈381 characters, or 4.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Harness Experiment

Harness engineering moves forward by experiment. The principle: measure first, change one thing at a time, keep what survives testing.

Companion to MCode Engineering Notes 01, 02 and 05.

1. Before changing anything

  1. State the hypothesis in one sentence: what you change, what you expect to improve, and what might get worse.
  2. Pick or build a small end-to-end eval. A handful of golden tasks is enough to start. Include tasks for every chain the agent runs in production and every rule it must not break. The checks must not be written by the agent under test; tests an agent writes for itself share its blind spots.
  3. Pin everything else. Same model version, same settings, same tool set, same repository state. If the model itself changes, treat that upgrade as the one change and rerun the same eval.
  4. Record a baseline. Run each task several times; agent runs are noisy and one run can hide a failure.

2. Make exactly one change

One prompt edit, one tool moved, one subagent merged, one threshold changed. If you need several, run several experiments.

3. Measure the same things on both sides

For baseline and candidate, record:

Metric Why
Pass rate per task (over repeated runs) Quality, with noise visible
Flipped tasks (pass to fail, fail to pass) Averages hide regressions
Model requests per task Many wins come from fewer round trips
Input and output tokens Cost and context pressure
Cache hit rate A change can save tokens but break caching
Wall-clock time Latency the user feels

Only report numbers you actually measured, with run counts.

4. Read the result

  • Open every flipped task and read the trajectory, not just the final answer (see trajectory-review). Find out why it flipped.
  • A change that keeps the score flat but cuts requests or tokens can be a win. A change that raises the average while breaking a must-not-break rule is not.
  • If the evidence is mixed, keep the simpler version.
  • Write the result down: hypothesis, change, numbers, flipped tasks, decision. Next to the code (a PR description or an experiments log) is best.

5. Re-check after model upgrades

Scaffolding built around a model's weak spots ages fastest. After each model upgrade, rerun the eval and ask which parts of the harness still earn their keep.

Output

A short experiment record: hypothesis, the single change, eval set and run count, the metric table for baseline and candidate, flipped tasks with causes, and the decision (keep / revert / iterate).

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts21d3 checks · Risk SAFE
  • Gen Agent Trust Hub21d

    This skill provides purely instructional guidance and methodology for conducting controlled experiments on agent configurations. It contains no executable code, network operations, or sensitive data access.

  • Socket21d

    No alerts

  • Snyk21d

    Risk: LOW · No issues

Signed by skilld at 0db1b4f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 3 weeks ago

README badge

README badge for minimax-ai/mcode-stack/harness-experiment