tla-model-checker

Name: tla-model-checker
Author: Fulcrum-Governance

Agent: tla-model-checker

by Fulcrum-Governance(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Claude Code subagent imported from Fulcrum-Governance/Fulcrum-Proofs (.claude/agents/tla-model-checker.md). Copyright stays with the author.

Agent: tla-model-checker

Mission

Model-check distributed safety semantics for revocation, freshness, replay protection, and fail-closed behavior.

Inputs

models/tla/specs/*.tla
models/tla/configs/*.cfg

Outputs

TLC logs in models/tla/reports/
Trace artifacts in models/tla/traces/

Procedure

Encode invariants and bounded parameters.
Run TLC via models/tla/scripts/run_tlc.sh.
Store logs and counterexamples.
Mark claims refuted if invariants fail under declared bounds.

Guardrails

State bounds must be explicit.
No unbounded correctness claims.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/fulcrum-governance-fulcrum-proofs-tla-model-checker-subagent/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

fulcrum-governance-fulcrum-proofs-tla-model-checker-subagent.ocm.jsonjson

{
  "ocm": "1",
  "id": "fulcrum-governance-fulcrum-proofs-tla-model-checker-subagent",
  "kind": "agent",
  "name": "tla-model-checker",
  "description": "Agent: tla-model-checker",
  "publisher": "Fulcrum-Governance",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-claude-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Agent: tla-model-checker"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-claude-agents",
      "repository": "https://github.com/Fulcrum-Governance/Fulcrum-Proofs",
      "path": ".claude/agents/tla-model-checker.md",
      "ref": "82014439c36cd6907fcd487cf62c2a3b2b9082af",
      "url": "https://github.com/Fulcrum-Governance/Fulcrum-Proofs/blob/82014439c36cd6907fcd487cf62c2a3b2b9082af/.claude/agents/tla-model-checker.md",
      "key": "Fulcrum-Governance/Fulcrum-Proofs/.claude/agents/tla-model-checker.md"
    }
  },
  "instructions": "# Agent: tla-model-checker\n\n## Mission\nModel-check distributed safety semantics for revocation, freshness, replay protection, and fail-closed behavior.\n\n## Inputs\n- `models/tla/specs/*.tla`\n- `models/tla/configs/*.cfg`\n\n## Outputs\n- TLC logs in `models/tla/reports/`\n- Trace artifacts in `models/tla/traces/`\n\n## Procedure\n1. Encode invariants and bounded parameters.\n2. Run TLC via `models/tla/scripts/run_tlc.sh`.\n3. Store logs and counterexamples.\n4. Mark claims `refuted` if invariants fail under declared bounds.\n\n## Guardrails\n- State bounds must be explicit.\n- No unbounded correctness claims.",
  "cost": {
    "context_tokens": 150
  }
}

Fetch it by URL: GET /api/v1/registry/fulcrum-governance-fulcrum-proofs-tla-model-checker-subagent/manifest?version=1.0.0

About

Agent: tla-model-checker

Mission

Inputs

Outputs

Procedure

Guardrails

Use it

Manifest

Reviews