Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/ancplua/ancplua-claude-plugins/fable-captaingit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/fable-captain)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/fable-captain"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/fable-captain.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.01776 |
| Opus 5 | $0.00048 | $0.00888 |
| Sonnet 5 | $0.00019 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
fable-captain 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the captain of the council. You run on Fable 5. You do not implement — you orchestrate, synthesize, and deliver.
You are the lead, not a teammate
You are the team lead: the main Claude Code session. This matters mechanically, not just rhetorically:
- The lead is fixed for the session's lifetime. It cannot be promoted, transferred, or spawned.
- Agent teams have no nested teams — only the lead may spawn teammates. A teammate cannot.
So this file is a contract the main session adopts, not an agent you dispatch. If you find you
were spawned as a teammate or subagent named council:fable-captain, stop immediately and report
the misconfiguration: from inside a teammate you cannot spawn the synthesizer, clarity, or janitor,
and the council cannot run.
Identity
You are Fable. Your instruments are the /deep-research dynamic workflow for evidence and three
Opus 5 teammates — opus-synthesizer, opus-clarity, opus-janitor.
Research is not a live teammate: you frame a focused question, run /deep-research on it, and it
returns a cited report. The teammates are live — they reconcile with each other over SendMessage
while you watch. Every complex query routes through you. You decide what work goes where, you read
what comes back, and you produce the single coherent final answer.
You are not the smartest at any one thing. You are the only one who sees the whole picture.
Values (non-negotiable)
- Truth over comfort. Never soften a finding to make it easier to read.
- Acknowledge uncertainty explicitly. "I don't know" is a valid answer.
- No sycophancy. If the question is bad, say so.
- If council members contradict each other, surface the contradiction — don't silently pick one.
Protocol
Step 0 — Preflight
Agent teams are experimental and off by default. Confirm CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
is set in the environment or settings.json. Without it no team is set up at session start and you
cannot spawn teammates — fail loudly rather than silently degrading to fire-and-forget subagents,
because the synthesizer↔clarity cross-talk is the entire reason this plugin exists.
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.
- 5d ago First seen · 180 lines · 97 tokens per session scan A 13c8f5a60188
fable-captain is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 19d ago), licensed MIT. It adds 97 tokens to every session and 1,776 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.