Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
lllllllama avatar

Minimal Run And Audit

  • 176k installs
  • 512 repo stars
  • Updated July 26, 2026
  • lllllllama/rigorpilot-skills

This is a copy of minimal-run-and-audit by lllllllama - installs and ranking accrue to the original listing.

minimal-run-and-audit is a Rigor Run agent skill that runs conservative smoke, inference, evaluation, or sanity checks on an agent and writes auditable evidence files for developers who need documented proof that a non-t

About

minimal-run-and-audit is the Rigor Run leaf mode from rigorpilot-skills for developers validating agent inference and evaluation pipelines before trusting results. The skill runs a selected smoke, inference, evaluation, or sanity command conservatively, captures execution evidence, and writes four artifacts: SUMMARY.md, COMMANDS.md, LOG.md, and status.json. Reporting policy requires separating facts from inferences, naming the documented command explicitly, and stating whether the run was full, partial, smoke-only, sanity-only, or blocked. Developers reach for minimal-run-and-audit when an agent change needs a reproducible audit trail instead of ad-hoc terminal output, especially after patches or when a blocker must be surfaced clearly in SUMMARY.md without burying the root cause.

  • Runs selected smoke, inference, evaluation or sanity commands conservatively
  • Captures execution evidence and writes SUMMARY.md, COMMANDS.md, LOG.md plus status.json
  • Separates facts from inferences and explicitly names the documented command
  • Reports whether run was full, partial, smoke-only, sanity-only or blocked
  • Keeps reports short, factual and easy to audit while avoiding narrative journals

Minimal Run And Audit by the numbers

  • 175,906 all-time installs (skills.sh)
  • +25,326 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill minimal-run-and-audit

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs176k
repo stars512
Security audit1 / 3 scanners passed
Last updatedJuly 26, 2026
Repositorylllllllama/rigorpilot-skills

How do you audit agent inference runs with evidence files?

Run conservative smoke, inference, evaluation or sanity checks on an agent and produce clean, auditable evidence files.

Who is it for?

Developers running Rigor Pilot agent pipelines who need short, factual, auditable reports after smoke, inference, evaluation, or sanity execution.

Skip if: Developers seeking open-ended exploratory experiments or multi-variant tuning without a fixed conservative run policy.

When should I use this skill?

User authorizes a conservative smoke, inference, evaluation, or sanity run and wants auditable execution evidence written to disk.

What you get

SUMMARY.md, COMMANDS.md, LOG.md, and status.json documenting run type, commands, logs, and blocked or partial status.

  • SUMMARY.md
  • COMMANDS.md
  • LOG.md

By the numbers

  • Writes 4 evidence files: SUMMARY.md, COMMANDS.md, LOG.md, and status.json

Files

SKILL.mdMarkdownGitHub ↗

minimal-run-and-audit

Use this as the Rigor Run skill. The installed slug remains minimal-run-and-audit for compatibility.

Use the shared operating principles in ../../references/agent-operating-principles.md; this skill should make run evidence auditable without turning every command into a rigid protocol.

When to apply

  • After a reproduction target and setup plan exist.
  • When the main skill needs execution evidence and normalized outputs.
  • When a smoke test, documented inference run, documented evaluation run, or other short non-training verification is appropriate.
  • When the user already knows what command should be attempted and wants execution plus reporting only.

When not to apply

  • During initial repo scanning.
  • When environment or assets are still undefined enough to make execution meaningless.
  • When the task is a literature lookup rather than repository execution.
  • When the user is still deciding which reproduction target should count as the main run.

Clear boundaries

  • This skill owns normalized reporting for an attempted command.
  • It may receive execution evidence from the main skill or a thin helper.
  • It does not choose the overall target on its own.
  • It does not perform broad paper analysis.
  • It does not own training startup, resume, or long-running training state.
  • It should not normalize risky code edits into acceptable practice.
  • It must not hide changes that alter evaluation, preprocessing, checkpoints,

metrics, or other scientific meaning.

Input expectations

  • selected reproduction goal
  • runnable commands or smoke commands
  • environment and asset assumptions
  • optional patch metadata

Output expectations

  • execution result summary
  • standardized repro_outputs/ files
  • SCIENTIFIC_CHANGELOG.md for changed scientific meaning and evidence status
  • COMPARABILITY_REPORT.md for README/paper/baseline comparability
  • clear distinction between verified, partial, and blocked states
  • PATCHES.md when repo files changed

Notes

Use references/reporting-policy.md, ../../references/research-rigor-principles.md, scripts/run_command.py, and scripts/write_outputs.py.

Related skills

How it compares

Pick minimal-run-and-audit over exploratory run skills when the goal is auditable verification evidence, not branching experiment comparison.

FAQ

What files does minimal-run-and-audit produce?

minimal-run-and-audit writes SUMMARY.md, COMMANDS.md, LOG.md, and status.json after a conservative smoke, inference, evaluation, or sanity run. SUMMARY.md states run type, blockers, and patch state; COMMANDS.md lists the documented command.

When should minimal-run-and-audit run instead of explore-run?

minimal-run-and-audit fits fixed conservative verification with auditable evidence. explore-run fits authorized isolated experiments with CHANGESET.md and TOP_RUNS.md when exploratory execution is explicitly approved.

Is Minimal Run And Audit safe to install?

skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.