mcpField
E
explore-code

explore-code

github.com/lllllllamaTesting & quality486339.4k installsUpdated 5w ago
Repository

About explore-code

explore-code is the Rigor Improve implementation leaf skill for bounded candidate code changes made on an isolated branch or worktree after explicit researcher authorization. It favors source-anchored module transplants, backbone adaptation, and LoRA or adapter insertion over freeform rewrites. Its results are recorded as candidates rather than verified contributions.

Key features

  1. 01Code changes on isolated branch or worktree
  2. 02Source-anchored module transplant
  3. 03LoRA and adapter insertion
  4. 04Records scientific meaning and rollback steps
  5. 05Outputs changeset and comparability reports

Use cases

  1. 01Transplanting an existing module into a baseline model as a candidate
  2. 02Making small backbone adaptations
  3. 03Trying low-risk module combinations without touching the trusted baseline

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lllllllama/rigorpilot-skills --skill explore-code

After installing, type/explore-codein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
explore-policy.md
scripts/
plan_code_changes.py
write_outputs.py

Details

From the project README

explore-code

Use this as the Rigor Improve implementation leaf skill. The installed slug remains explore-code for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide bounded candidate code work without over-prescribing implementation details.

When to apply

  • When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
  • When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
  • When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.

When not to apply

  • When the request is for trusted baseline work, conservative debugging, or normal training execution.
  • When the user did not explicitly authorize exploratory modifications.
  • When the task is a broad refactor or a from-scratch idea implementation.

Clear boundaries

  • This skill owns exploratory code modifications only.
  • It must keep work isolated from the trusted baseline.
  • Use ai-research-explore instead when the task spans both current_research coordination and exploratory runs.
  • It may hand off execution to minimal-run-and-audit or run-train.
  • It should favor source-anchored copying and minimal adaptation over freeform rewrites.
  • It should record why a candidate change is meaningful, how to roll it back, and why it remains a candidate rather than a verified contribution.

Output expectations

  • explore_outputs/CHANGESET.md
  • explore_outputs/SCIENTIFIC_CHANGELOG.md
  • explore_outputs/COMPARABILITY_REPORT.md
  • explore_outputs/TOP_RUNS.md
  • explore_outputs/status.json

Notes

Use references/explore-policy.md, ../ai-research-reproduction/references/research-rigor-principles.md, scripts/plan_code_changes.py, and scripts/write_outputs.py.

Comments

Markdown supported