Agent Plugins Marketplace
← All plugins

bootloops-protocols

v1.0.0

The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.

CodexClaude CodeAgent Plugins7 Skills

By Matthew D. SchwartzLicense: CC-BY-4.0 AND MIT11 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Codex, Claude Code, and Agent Plugins
Parsed components
7 skill or MCP entries
Source updated
Oct 1, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install bootloops-protocols for Codex and Claude Code

Installs for the current user
codex plugin marketplace add BootLoops-ai/skills
codex plugin marketplace upgrade bootloops
codex plugin add bootloops-protocols@bootloops

Paste and run these commands in a terminal with Codex. They add and refresh the bootloops catalog, then install this plugin.

Compatibility: the page URL and API slug “bootloops-protocols” remain stable.

  • Codex: bootloops-protocols@agent-plugin-marketplace → bootloops-protocols@bootloops

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/BootLoops-ai/skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/bootloops-protocols/.

Plugin files

plugins/bootloops-protocols/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── plugin.json
├── skills/acceptance-gate/SKILL.md
├── skills/constant-recognition/SKILL.md
├── skills/independence-bookkeeping/SKILL.md
├── skills/planted-truth/SKILL.md
├── skills/reading-contract/SKILL.md
├── skills/timing-discipline/SKILL.md
└── skills/tool-stewardship/SKILL.md

Included Skills7

acceptance-gateskills/acceptance-gate/SKILL.md

The standard a computed result must meet before it may be called done. Use whenever an agent claims an integral is solved, a fit has closed, a formula is identified, or any quantitative answer is ready — the claim is not done until it passes this gate.

constant-recognitionskills/constant-recognition/SKILL.md

Discipline for integer-relation searches (PSLQ, LLL) that turn high-precision digits into exact constants. Use whenever recognizing a numerical value as a closed form, fitting boundary constants, or reporting that no closed form exists.

independence-bookkeepingskills/independence-bookkeeping/SKILL.md

Provenance rules that keep checks independent. Use when setting up any comparison, oracle, or reference value — and whenever tempted to certify a result with machinery that helped produce it.

planted-truthskills/planted-truth/SKILL.md

Synthetic-truth controls for analysis pipelines. Use before running any statistical fit, solver, audit, or search on real data — the pipeline must first prove it can recover a known planted answer and catch a deliberately corrupted input.

reading-contractskills/reading-contract/SKILL.md

Sources-only discipline for any instrument or agent that reads documents and asserts facts from them — literature audits, record replays, data extraction, citation of prior work.

timing-disciplineskills/timing-discipline/SKILL.md

Compute-planning rules. Use before launching any calculation whose runtime is not already measured — and whenever an agent proposes a long run, an overnight grind, or a bigger machine as the way forward.

tool-stewardshipskills/tool-stewardship/SKILL.md

How the toolkit is consulted, extended, and documented. Use before writing any new code — and after, when a genuinely new instrument has earned its place.

Plugin manifests3

plugins/bootloops-protocols/.codex-plugin/plugin.json
{
  "name": "bootloops-protocols",
  "version": "1.0.0",
  "description": "The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "BootLoops protocols",
    "shortDescription": "Seven disciplines for trustworthy quantitative work with agents.",
    "longDescription": "The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.",
    "developerName": "Matthew D. Schwartz",
    "category": "Productivity",
    "websiteURL": "https://www.bootloops.ai"
  }
}
plugins/bootloops-protocols/.claude-plugin/plugin.json
{
  "name": "bootloops-protocols",
  "version": "1.0.0",
  "description": "The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ]
}
plugins/bootloops-protocols/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "bootloops-protocols",
  "version": "1.0.0",
  "description": "The BootLoops protocol layer: seven disciplines for trustworthy quantitative work with agents — acceptance gates, integer-relation discipline, synthetic-truth controls, provenance bookkeeping, timing discipline, sources-only reading, tool stewardship.",
  "author": {
    "name": "Matthew D. Schwartz",
    "url": "https://www.bootloops.ai"
  },
  "homepage": "https://www.bootloops.ai",
  "repository": "https://github.com/BootLoops-ai/skills",
  "license": "CC-BY-4.0 AND MIT",
  "keywords": [
    "science",
    "verification",
    "protocols",
    "agent-skills",
    "bootloops"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[bootloops-protocols on Agent Plugins Marketplace](https://pluginsmp.com/plugins/bootloops-protocols)