harness-experiment SKILL.md skillA
harness-experiment from minimax-ai/mcode-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add minimax-ai/mcode-stack/harness-experiment@git:20261029.49a3ff4Pins git:20261029.49a3ff4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- minimax-ai/mcode-stack
- Path
stacks/ronny/skills/harness-experiment/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261029.49a3ff4, committed Oct 29, 2026
- First version recorded
- Oct 28, 2026
- Size
- 3,024 bytes
- Repository stars
- 495
- License
- MIT
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 …
Read the whole file at its exact version.
How to install
mdr add minimax-ai/mcode-stack/harness-experiment@sha256:2fa0e460767594fdThe line at the top of this page pins the label git:20261029.49a3ff4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2xs2y6jnoxafyewz)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 28, 2026 and Oct 29, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261029.49a3ff4 latest | 2026-10-29 | 49a3ff4 | 3,024 B | A | view · diff |
| git:20261028.c889a19 | 2026-10-28 | c889a19 | 3,024 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3024 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
minimax-ai/mcode-stack · 495 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2xs2y6jnoxafyewz GET https://markdownregistry.com/api/v1/resolve?ref=minimax-ai/mcode-stack/harness-experiment GET https://markdownregistry.com/api/v1/blob/2fa0e460767594fdf9ee235e78215d29c118ccf7b0cd93f919ec0c07a430ae88
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.