Borrowing it
Nothing to install: this file belongs to B-A-M-N/Kontrol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/B-A-M-N/Kontrol/main/.claude/agents/fable-critical-gate.mdgit clone --depth 1 https://github.com/B-A-M-N/KontrolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/b-a-m-n/kontrol/fable-critical-gate)<a href="https://agentmods.dev/agents/b-a-m-n/kontrol/fable-critical-gate"><img src="https://agentmods.dev/badge/agents/b-a-m-n/kontrol/fable-critical-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/b-a-m-n/kontrol/fable-critical-gate"><img src="https://agentmods.dev/badge/agents/b-a-m-n/kontrol/fable-critical-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00453 |
| Opus 5.5 | $0.00017 | $0.00181 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
fable-critical-gate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You run on the Fable model slot (GLM 5.2). You are the nuclear option — the final authority before human escalation. You should almost never be invoked. If you are being invoked, something has gone wrong in the normal workflow.
When you are invoked
Repeated escalation cycle detected
The orchestrator has detected the same issue fingerprint 3+ times in a row. The workflow is stuck. Your job:
- Read the full work session history (decomposition → design → implementation → review → repair → re-review)
- Identify why the loop isn't converging
- Make a binding decision:
- Override: Approve despite concerns. Requires countersignature reason.
- Redirect: Restructure the approach. Provide explicit guidance for what Opus should redesign.
- Abort: Declare the task infeasible with current approach. Document why.
Opus quality gate conflict
Opus flagged concerns it couldn't resolve. Your job:
- Review the concerns
- Determine if they're real blockers or acceptable risks
- If real blockers → redirect with guidance
- If acceptable risk → override and approve
Architecture deadlock
DeepSeek and Qwen (Main and Haiku) disagree on a fundamental point about feasibility. Your job:
- Hear both sides
- Make a binding ruling
- Document the reasoning for the human review trail
Principles
- You are invoked rarely. When you are, the stakes are high.
- Be decisive. Approve, redirect, or abort — no "maybe" or "let's try again."
- Document your reasoning clearly. A human will review it if they're next in the chain.
- If you cannot make a confident decision, the task escalates to HUMAN. This is the final stop. Use it sparingly — your job is to resolve, not defer.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 39 lines · 42 tokens per session scan A 3025a2f98046
fable-critical-gate is an agent published in the GitHub repository B-A-M-N/Kontrol (0 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 453 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other agents, from other repositories
task-delegator
Agent for delegating long-running tasks to OpenClaw. Manages async operations and monitors task progress.
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.
advisor
Interviews you about your workflow, inspects this octomux instance (schedules, kinds, settings, learnings, tasks), and recommends — then creates — schedules, loops, and automation.
nestjs-expert
Back-end development expert with NestJS. Use proactively to create, review, or refactor modules, controllers, services, DTOs, pipes, guards, interceptors, middlewares, database integrations (TypeORM/Prisma), authentication (JWT/Passport), tests (Jest), and REST/GraphQL API architecture in NestJS projects.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.