agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/ideabrowser-connector/SKILL.md

ideabrowser-connector

Skill29 starsChanged 7 months agoMITView on GitHub

Secure IdeaBrowser agent connector with read-only vs mutating classification, zero plaintext credentials, and fail-closed pre-action diodes. Closes ThumbGate issue #3823.

  • Reads credentials

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every discovered tool/action from IdeaBrowser must be classified into one of two operational tiers:

    line 19
  2. Very specific:

    Before executing any mutating tool, executeTool evaluates:

    line 25
  3. Distinctive:

    All interdiction event payloads recursively redact sensitive keys, query parameters, and error reasons before notifying listeners.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

IdeaBrowser Agent Connector & Governance Diode

Issue #3823 Resolution Reference: Implements a hardened IdeaBrowser connector for ThumbGate without credential leakage, classifying all actions into read-only or mutating tiers.

🛡️ Security & Governance Invariants

  1. Zero Plaintext Credentials:
    • Connector tokens/secrets must never be stored in tracked repository files or plaintext configuration files.
    • Resolve credentials via authenticated environment variables (IDEABROWSER_API_KEY) or secure secret storage.
  2. Strict Tool Classification:
    • Every discovered tool/action from IdeaBrowser must be classified into one of two operational tiers:
      • read-only: Information gathering, DOM inspection, status query, screenshot, URL retrieval. Allowed by default.
      • mutating: Form submission, button click, file upload, state mutation, purchasing, external navigation. Gated by ThumbGate pre-action interdiction.
    • Fail-Closed on Provider Drift: Any newly introduced or unclassified tool defaults immediately to mutating and triggers a gate check.
  3. Pre-Action Interdiction:
    • Before executing any mutating tool, executeTool evaluates:
      • Target domain against configured allowlist (empty allowlist fails closed).
      • Caller-provided context.blocked flag (upstream policy is responsible for evaluating blast radius, authorization, and scope state to set context.blocked).
    • All interdiction event payloads recursively redact sensitive keys, query parameters, and error reasons before notifying listeners.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free