Skip to content
Back to search

grainulation-marketplace

SkillGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/grainulation/grainulator with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/grainulation/grainulator'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/grainulation--grainulator/badge.svg)](/listings/grainulation--grainulator)

HTML

<a href="/listings/grainulation--grainulator"><img src="/api/listings/grainulation--grainulator/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Requires **Node.js 24+**. Node 25 is the development default.

**Upgrading from 1.x?** Follow the [migration checklist](docs/UPGRADING.md) to update the plugin and keep your existing research data.

git clone --branch v2.3.0 https://github.com/grainulation/grainulator.git
cd grainulator
npm ci --ignore-scripts
node bin/grainulator.js doctor

To use Grainulator inside your agent, follow the **[Claude Code or Codex setup guide](docs/AGENT-SETUP.md)**. The [website](https://grainulator.dev/) shows a saved example of an evidence check. It does not send your question to a model.

The local research playground remains available through `node bin/grainulator.js preview`. It runs models using a provider account you configure locally.

> **Distribution:** v2.3.0 is a [GitHub release](https://github.com/grainulation/grainulator/releases/tag/v2.3.0), not an npm registry release. For a separate local installation, follow the [archive installation guide](docs/INSTALLATION.md).

Other agents: connect through MCP

Add an MCP server that runs this command, with your project's absolute path:

npx -y github:grainulation/grainulator#v2.3.0 mcp --dir /absolute/path/to/project

Antigravity installs the full plugin. See the [agent setup guide](docs/AGENT-SETUP.md) for Antigravity, Cursor and other MCP agents.

For the full Claude Code or Codex plugin, use the **[agent setup guide](docs/AGENT-SETUP.md)**. Codex needs a project folder; the guide shows how to set it. CLI and direct MCP access remain available to other hosts.

Or point your coding agent (Claude Code, Codex, or Antigravity) at this checkout:

Read README.md and AGENTS.md in the Grainulator repository. Run node bin/grainulator.js doctor
and node bin/grainulator.js demo, and report the exit codes and final status lines. Then tell me
which routes below this machine can run, and ask me before starting any model-backed or paid run.

| Route | What it does | Needs | Time / Cost | | --- | --- | --- | --- | | **1. Local ledger & offline demo** | Runs `doctor`, `demo`, `init`, `add`, and `compile` | Node.js ≥24; no credentials | ~2 s · $0 (no model calls) | | **2. Managed command verifier** | Runs `grainulator run --adapter ... --verify ...` with soundness-break (`exit 3`) enforcement | Route 1 + local verifier script | Per-round timeout & round cap | | **3. Host plugin or MCP server** | Connects `add_claim`, `compile`, `resolve`, `memory`, and `exports` to Claude Code, Codex, Antigravity, or MCP hosts | Route 1 + host agent | Host session · $0 Grainulator overhead | | **4. Semantic & adversarial evals** | Runs `evals/rejected-claims` (offline) or `scripts/evaluate-semantic.mjs` (model-backed) | Route 1 (+ API credentials for live model matrix) | Offline $0 · live matrix requires explicit budget |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 36 lines
  1. {
  2. "name": "grainulation-marketplace",
  3. "owner": {
  4. "name": "Grainulation",
  5. "email": "info@grainulator.app"
  6. },
  7. "metadata": {
  8. "description": "Evidence and verification tools for model-assisted work",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "grainulator",
  14. "source": {
  15. "source": "url",
  16. "url": "https://github.com/grainulation/grainulator.git"
  17. },
  18. "description": "Evidence and verification for model-assisted work",
  19. "version": "2.4.0",
  20. "author": {
  21. "name": "Grainulation"
  22. },
  23. "homepage": "https://grainulator.dev",
  24. "repository": "https://github.com/grainulation/grainulator",
  25. "license": "MIT",
  26. "keywords": ["research", "grainulator", "claims", "evidence", "briefs"],
  27. "category": "research",
  28. "tags": [
  29. "research-sprints",
  30. "analysis",
  31. "documentation",
  32. "decision-making"
  33. ]
  34. }
  35. ]
  36. }
README.md · README · 170 lines
  1. <p align="center">
  2. <a href="https://grainulator.dev"><img src="public/glitchy.png" alt="Glitchy — the Grainulator mascot" width="200"></a>
  3. </p>
  4. <h1 align="center">Grainulator</h1>
  5. <p align="center"><strong>Evidence and verification for the model you already use.</strong></p>
  6. <p align="center">
  7. Keep the evidence. Challenge the answer. Know what to do next.<br>
  8. A shared workflow for research, engineering, and model-assisted work.
  9. </p>
  10. <p align="center">
  11. <a href="https://grainulator.dev/"><img src="https://img.shields.io/badge/website-grainulator.dev-98f3ef?style=for-the-badge" alt="See the Grainulator homepage"></a>
  12. </p>
  13. <p align="center">
  14. <a href="https://github.com/grainulation/grainulator/actions/workflows/ci.yml"><img src="https://github.com/grainulation/grainulator/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI on main"></a>
  15. <a href="docs/INSTALLATION.md"><img src="https://img.shields.io/badge/node-%E2%89%A524-339933?logo=nodedotjs&logoColor=white" alt="Node.js 24 or later"></a>
  16. <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="MIT license"></a>
  17. <a href="https://deepwiki.com/grainulation/grainulator"><img src="https://img.shields.io/badge/docs-DeepWiki-1f6feb" alt="Docs on DeepWiki"></a>
  18. </p>
  19. <p align="center">
  20. <a href="#quick-start">Quick start</a> ·
  21. <a href="docs/INSTALLATION.md">Installation</a> ·
  22. <a href="docs/UPGRADING.md">Upgrading</a> ·
  23. <a href="docs/TOOLS.md">Tools</a> ·
  24. <a href="docs/AGENT-SETUP.md">Agent setup</a> ·
  25. <a href="CHANGELOG.md">Changelog</a>
  26. </p>
  27. ---
  28. ## What it adds
  29. Good models still need a way to keep track of evidence, revisit assumptions, and verify their work. Grainulator gives them that process, with a local ledger that stays with the task as it moves between models and sessions.
  30. | Capability | What it gives you |
  31. | --- | --- |
  32. | **Evidence that stays with the work** | Typed claims, sources, evidence tiers, and provenance that survive edits and exports. |
  33. | **A check on the answer** | Conflict detection, weak-support signals, and explicit gaps to investigate. |
  34. | **Clear next actions** | Two lists: what the agent can continue automatically, and what needs your input. |
  35. | **Sessions you can carry forward** | Configurable research, stop/resume, reusable context, and credential-free exports. |
  36. | **Verification for your task** | A managed command loop that can use a verifier you provide. |
  37. Grainulator works with Claude Code and Codex through plugins. It also provides a command-line tool and an MCP connection for other agents. You do not need to install its components separately.
  38. ## Quick start
  39. Requires **Node.js 24+**. Node 25 is the development default.
  40. **Upgrading from 1.x?** Follow the [migration checklist](docs/UPGRADING.md) to update the plugin and keep your existing research data.
  41. ```sh
  42. git clone --branch v2.3.0 https://github.com/grainulation/grainulator.git
  43. cd grainulator
  44. npm ci --ignore-scripts
  45. node bin/grainulator.js doctor
  46. ```
  47. To use Grainulator inside your agent, follow the **[Claude Code or Codex setup guide](docs/AGENT-SETUP.md)**. The [website](https://grainulator.dev/) shows a saved example of an evidence check. It does not send your question to a model.
  48. The local research playground remains available through `node bin/grainulator.js preview`. It runs models using a provider account you configure locally.
  49. > **Distribution:** v2.3.0 is a [GitHub release](https://github.com/grainulation/grainulator/releases/tag/v2.3.0), not an npm registry release. For a separate local installation, follow the [archive installation guide](docs/INSTALLATION.md).
  50. ### Other agents: connect through MCP
  51. Add an MCP server that runs this command, with your project's absolute path:
  52. ```sh
  53. npx -y github:grainulation/grainulator#v2.3.0 mcp --dir /absolute/path/to/project
  54. ```
  55. Antigravity installs the full plugin. See the [agent setup guide](docs/AGENT-SETUP.md) for Antigravity, Cursor and other MCP agents.
  56. For the full Claude Code or Codex plugin, use the **[agent setup guide](docs/AGENT-SETUP.md)**. Codex needs a project folder; the guide shows how to set it. CLI and direct MCP access remain available to other hosts.
  57. Or point your coding agent (Claude Code, Codex, or Antigravity) at this checkout:
  58. ```text
  59. Read README.md and AGENTS.md in the Grainulator repository. Run node bin/grainulator.js doctor
  60. and node bin/grainulator.js demo, and report the exit codes and final status lines. Then tell me
  61. which routes below this machine can run, and ask me before starting any model-backed or paid run.
  62. ```
  63. | Route | What it does | Needs | Time / Cost |
  64. | --- | --- | --- | --- |
  65. | **1. Local ledger & offline demo** | Runs `doctor`, `demo`, `init`, `add`, and `compile` | Node.js ≥24; no credentials | ~2 s · $0 (no model calls) |
  66. | **2. Managed command verifier** | Runs `grainulator run --adapter ... --verify ...` with soundness-break (`exit 3`) enforcement | Route 1 + local verifier script | Per-round timeout & round cap |
  67. | **3. Host plugin or MCP server** | Connects `add_claim`, `compile`, `resolve`, `memory`, and `exports` to Claude Code, Codex, Antigravity, or MCP hosts | Route 1 + host agent | Host session · $0 Grainulator overhead |
  68. | **4. Semantic & adversarial evals** | Runs `evals/rejected-claims` (offline) or `scripts/evaluate-semantic.mjs` (model-backed) | Route 1 (+ API credentials for live model matrix) | Offline $0 · live matrix requires explicit budget |
  69. ## Put it to work
  70. With Grainulator connected, give your agent the outcome you need:
  71. > Use Grainulator to investigate whether we should migrate this service. Record the evidence, challenge the assumptions, implement the agreed changes, and verify them. Keep the remaining next steps split into Auto and Manual.
  72. The work follows a simple cycle:
  73. 1. **Record** findings with their sources and evidence tiers.
  74. 2. **Check** for conflicts, weak support, and missing perspectives.
  75. 3. **Act** on the gaps that matter, then verify the requested result.
  76. 4. **Continue** from the saved ledger or export the session to another workflow.
  77. There are no fixed claim-count or research-pass quotas. **Auto** lists work the agent can continue within your authorization. **Manual** lists decisions, access, or actions that need you. When you ask only for next steps, those two lists are the entire response.
  78. <details>
  79. <summary><strong>Example: record a claim from the terminal</strong></summary>
  80. ```sh
  81. node bin/grainulator.js init --dir ./sprints/migration \
  82. --question 'Should we migrate this service?' \
  83. --audience engineers --constraints 'Preserve existing user data' \
  84. --done 'A verified plan with remaining risks documented'
  85. node bin/grainulator.js add --dir ./sprints/migration \
  86. --id r001 --type constraint --topic migration \
  87. --content 'Existing user data must remain readable.' --evidence stated
  88. node bin/grainulator.js compile --dir ./sprints/migration
  89. ```
  90. The equivalent MCP tool is **`add_claim`** on the **`grainulator`** server. See the [tool reference](docs/TOOLS.md) for evidence, memory, export, analytics, and orchestration operations.
  91. </details>
  92. ## Explore the docs
  93. | Guide | Start here for… |
  94. | --- | --- |
  95. | [Installation](docs/INSTALLATION.md) | Tagged source, isolated archives, and verified build identity. |
  96. | [Upgrading from 1.x](docs/UPGRADING.md) | Host updates, renamed tools, existing data, and retired setup instructions. |
  97. | [Agent setup](docs/AGENT-SETUP.md) | Use Grainulator with Claude Code, Codex, or another agent. |
  98. | [Research sessions](docs/RESEARCH.md) | Models, feature controls, credentials, export, and resume. |
  99. | [Tools](docs/TOOLS.md) | The canonical CLI and MCP interface. |
  100. | [Execution adapters](docs/ADAPTERS.md) | Attaching a model command and a task-specific verifier. |
  101. | [Architecture](docs/STRUCTURE.md) | The workspace layout and internal modules. |
  102. | [Evaluation](docs/EVALUATION.md) | What has been measured and what remains unproven. |
  103. | [Contributing](CONTRIBUTING.md) | Development setup, tests, and changes to the project. |
  104. ## Verification and limits
  105. CI checks Node 24 and 25, isolated package installation, plugin contracts, Rust runtime conformance, lint, and the static playground in a browser. Native host and live-provider acceptance have separate [verification guides](docs/READINESS.md).
  106. The compiler checks the structure and support recorded in the ledger; it does not establish that a source is true. Evaluations do not establish a general accuracy or efficiency gain, and per-pass limits are not a whole-session spending cap. Keep those distinctions when interpreting results.
  107. <details>
  108. <summary><strong>Run the development checks</strong></summary>
  109. ```sh
  110. npm test
  111. npm run test:install
  112. npm run lint
  113. ```
  114. Browser and runtime prerequisites are in [CONTRIBUTING.md](CONTRIBUTING.md). The offline `node bin/grainulator.js demo` exercises the adapter/verifier protocol without a provider account.
  115. </details>
  116. ---
  117. <p align="center">
  118. Built by <a href="https://grainulation.com">Grainulation</a> ·
  119. <a href="LICENSE">MIT licensed</a> ·
  120. <a href="https://github.com/grainulation/grainulator/issues">Issues & ideas</a>
  121. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.