Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add agent: research harness engineer - #2854

Merged
aaronpowell merged 3 commits into
github:mainfrom
GuoCheng24:add-research-experiment-discipline
Aug 31, 2026
Merged

Add agent: research harness engineer#2854
aaronpowell merged 3 commits into
github:mainfrom
GuoCheng24:add-research-experiment-discipline

Conversation

@GuoCheng24

Copy link
Copy Markdown
Contributor

Adds instructions/research-experiment-discipline.instructions.md — guidance for repositories where Copilot writes evaluation harnesses, benchmark sweeps, or any code that reports a performance number.

Falls under "Development methodologies and best practices" / "Testing strategies and quality assurance" in CONTRIBUTING. The gap it addresses: in research code the common failure is not a crash but a number that looks great and is wrong — models happily write evaluation code that tunes on the test set, compares against unmatched baselines, or reports point estimates inflated by group leakage. The instructions are specific and mechanical: null models scored first (freeze on a well-scoring null), calibration/held-out separation on the unit of independence, a held-out access budget, published-baseline reproduction before improvement claims, paired error bars, and every new check demonstrated to fail on a deliberately broken input.

Distilled from real failures in agent-run experiment campaigns; the longer-form methodology with runnable demonstrations lives at https://github.com/GuoCheng24/breakthrough-harness.

  • Branch created from main
  • npm start run; docs/README.instructions.md updated (the script also produced unrelated churn in docs/README.agents.md from live MCP-registry data — left out to keep the diff minimal; happy to include if the check requires it)

@github-actions github-actions Bot added instructions PR touches instructions new-submission PR adds at least one new contribution labels Aug 29, 2026
@github-actions

Copy link
Copy Markdown
Contributor

🔒 PR Risk Scan Results

Scanned 1 changed file(s).

Severity Count
🔴 High 0
🟠 Medium 0
ℹ️ Info 0

✅ No matching risk patterns were detected in changed files.

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

@aaronpowell aaronpowell left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I wonder if instructions are the right way to be adding this, maybe a custom agent would be a better approach.

The risk the instructions provide is that they are applied broadly on any file that is being worked on. but it reads a bit like the goal is to steer the agent down a thinking path, which would be better from the agent definition

@GuoCheng24

Copy link
Copy Markdown
Contributor Author

Good call — agreed that the content is steering a way of thinking rather than per-file conventions, and broad applyTo was the weak point. Converted to a custom agent: agents/research-harness-engineer.agent.md (instructions file removed, npm start re-run). The regenerated docs/README.agents.md includes a few pre-existing formatting diffs from the generator pulling live MCP-registry data; happy to rebase them out if you'd rather keep the diff to just the new row.

@GuoCheng24 GuoCheng24 changed the title Add instructions: research experiment discipline Add agent: research harness engineer Aug 31, 2026
@github-actions github-actions Bot added agent PR touches agents and removed instructions PR touches instructions labels Aug 31, 2026
@github-actions

Copy link
Copy Markdown
Contributor

🔍 Vally Lint Results

⚠️ Warnings or advisories found

Scope Checked
Skills 0
Agents 1
Total 1
Severity Count
❌ Errors 0
⚠️ Warnings 0
ℹ️ Advisories 1

Summary

Level Finding
ℹ️ Vally currently lints SKILL.md content. Agent files were detected but skipped:
Full linter output
### Agent files detected (not linted by vally)
ℹ️ Vally currently lints SKILL.md content. Agent files were detected but skipped:
agents/research-harness-engineer.agent.md

aaronpowell
aaronpowell previously approved these changes Aug 31, 2026

@aaronpowell aaronpowell left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you re-run the script to update the readme, there seems to be an accidental change included

@GuoCheng24

Copy link
Copy Markdown
Contributor Author

Done — docs/README.agents.md is now upstream plus only the new agent row; the accidental generator churn (live MCP-registry formatting) is gone.

@GuoCheng24

Copy link
Copy Markdown
Contributor Author

@all-contributors add @GuoCheng24 for agents

@allcontributors

Copy link
Copy Markdown
Contributor

@GuoCheng24

I couldn't determine any contributions to add, did you specify any contributions?
Please make sure to use valid contribution names.

@aaronpowell
aaronpowell merged commit 32f32c9 into github:main Aug 31, 2026
16 checks passed
@GuoCheng24

Copy link
Copy Markdown
Contributor Author

@all-contributors please add @GuoCheng24 for agents

@allcontributors

Copy link
Copy Markdown
Contributor

@GuoCheng24

I couldn't determine any contributions to add, did you specify any contributions?
Please make sure to use valid contribution names.

@GuoCheng24

Copy link
Copy Markdown
Contributor Author

@all-contributors add @GuoCheng24 for content

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

agent PR touches agents new-submission PR adds at least one new contribution

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants