sweep SKILL.md skillA

sweep from borda/ai-rig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add borda/ai-rig/sweep@git:20261012.8e6b67e

Pins git:20261012.8e6b67e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
borda/ai-rig
Path
plugins/cc_research/skills/sweep/SKILL.md
Versions recorded
13
Latest version
git:20261012.8e6b67e, committed Oct 12, 2026
First version recorded
Aug 6, 2026
Size
23,533 bytes
Repository stars
28
License
Apache-2.0

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

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

<objective>

Non-interactive end-to-end research pipeline: auto-plan → judge gate → run. Single command from goal to result. Accepts goal string, passes all run/colab/team flags.

NOT for: interactive planning (use `/research:plan`); methodology review only (use `/research:judge`); running already-approved plan (use `/research:run`).

</objective>

<compaction>

- Key boundaries: end of S2 — program.md written and confirmed; end of S3 — judge+refinement verdict settled.
- Preserve at S2: program-path (output of plan), GOAL string, OUT path (TMPDIR key).
- Mid-loop refresh: after each S3 fix-apply the contract is rewritten with refine-iter/no-fixes-iter/last-verdict (placed after fixes so the "fixes applied" claim is true) — a mid-loop compaction resumes at the current iteration instead of restarting REFINE_ITER=0.
- Preserve at S3: judge verdict, JUDGE_REPORT path, program-path, GOAL.
- Clear at S1 start (stale prior run) and after S5 pipeline completes.

</compaction>

<workflow>

## Agent Resolution

<!-- Agent resolution: see _RESEARCH_SHARED/agent-resolution.md -->
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add borda/ai-rig/sweep@sha256:55ebf00201bca295

The line at the top of this page pins the label git:20261012.8e6b67e, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2uwqpnqhmux4iav7.svg)](https://markdownregistry.com/a/art_2uwqpnqhmux4iav7)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 13 versions of this file, between Aug 6, 2026 and Oct 12, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20261012.8e6b67e latest2026-10-12 8e6b67e 23,533 BA view · diff
git:20261009.253fdb32026-10-09 253fdb3 23,275 BA view · diff
git:20261002.381549d2026-10-02 381549d 23,083 BA view · diff
git:20260930.5b124562026-09-30 5b12456 21,952 BA view · diff
git:20260929.98a9e772026-09-29 98a9e77 21,891 BA view · diff
git:20260923.39e3a482026-09-23 39e3a48 21,805 BA view · diff
git:20260918.3e1a63d2026-09-18 3e1a63d 21,629 BA view · diff
git:20260911.182df572026-09-11 182df57 21,634 BA view · diff
git:20260821.d9793192026-08-21 d979319 22,271 BA view · diff
git:20260808.a8a70fe2026-08-08 a8a70fe 22,259 BA view · diff
git:20260808.c2ee8972026-08-08 c2ee897 22,391 BA view · diff
git:20260808.1b905ff2026-08-08 1b905ff 22,363 BA view · diff
git:20260806.848a1702026-08-06 848a170 22,527 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (23533 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

GitHub

borda/ai-rig · 28 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2uwqpnqhmux4iav7
GET https://markdownregistry.com/api/v1/resolve?ref=borda/ai-rig/sweep
GET https://markdownregistry.com/api/v1/blob/55ebf00201bca295171eb9008fca90af74e921c3223a86d3b9785c9fe4ab8147

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.

More from borda/ai-rig

AGENTS.md AGENTS.md file
borda/ai-rig · AGENTS.md
git:20261016.002ddc5 · audit A · 28 stars
CLAUDE.md CLAUDE.md file
borda/ai-rig · CLAUDE.md
git:20261016.002ddc5 · audit A · 28 stars
AGENTS.md@benchmarks AGENTS.md file
borda/ai-rig · benchmarks/AGENTS.md
git:20260814.b9c6b5a · audit A · 28 stars
llms.txt@docs llms.txt file
borda/ai-rig · docs/llms.txt
git:20260814.1bd25c1 · audit A · 28 stars
AGENTS.md@plugins AGENTS.md file
borda/ai-rig · plugins/AGENTS.md
git:20261021.7b6ff28 · audit A · 28 stars
CLAUDE.md@plugins CLAUDE.md file
borda/ai-rig · plugins/CLAUDE.md
git:20261021.7b6ff28 · audit B · 28 stars
advise SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/advise/SKILL.md · Ask Codex a read-only question with explicit model, effort, budget, and compact results.
git:20261015.0b59b78 · audit A · 28 stars
cancel SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/cancel/SKILL.md · Request cancellation of a running detached Codex bridge job.
git:20261021.7b6ff28 · audit A · 28 stars
implement SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/implement/SKILL.md · Ask Codex for one bounded write-capable change with compact results.
git:20261015.0b59b78 · audit A · 28 stars
result SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/result/SKILL.md · Read a completed detached Codex bridge job's compact result.
git:20261021.7b6ff28 · audit A · 28 stars
review SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/review/SKILL.md · Request a read-only adversarial Codex review with explicit model, effort, budget, and compact findings.
git:20261015.0f0cec6 · audit A · 28 stars
setup SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/setup/SKILL.md · Configure, authenticate, repair, and verify the Claude Code to Codex Bridge; safe stages run by default and sensitive…
git:20261011.9360690 · audit A · 28 stars

Every file in borda/ai-rig

Other files named sweep

sweep SKILL.md skill
simota/agent-skills · sweep/SKILL.md · Detecting unnecessary files, unused code, and orphaned files, and proposing safe deletion. Not for removal execution…
git:20261012.27f6d8a · audit A · 95 stars
sweep SKILL.md skill
dkstm95/hope · plugins/hope/skills/sweep/SKILL.md · Apply proven, behavior-preserving codebase cleanup. Use only when explicitly invoked.
git:20260928.ff3dfa2 · audit A · 8 stars
sweep SKILL.md skill
leek/agent-skills · skills/sweep/SKILL.md · Dig for one problem nobody has noticed yet (a latent bug, silent production error, slow path, or test gap), prove it…
git:20261019.0f2f385 · audit A · 4 stars

Browse by kind, by grade A, or by owner.