consult-fable

consult-fable is a skill for Claude Code, Codex from synaptent/aragora. It costs 126 tokens per session (1,543 once invoked), scanned A, original, MIT.

A bounded consultation tool that asks Claude Fable 5, another AI model, for advice from inside the Aragora repository. It returns a second opinion through controlled attempts and time limits.

In plain words
What is it for?
Use it to prioritize the next task, review a proposed plan, get a second design opinion, or break a reviewer deadlock.
Why use it?
It gives you an outside view when you are stuck choosing work, resolving a design disagreement, or checking whether a plan makes sense. The limits help prevent an unanswered consultation from running indefinitely.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/synaptent/aragora/consult-fable
Any agent
npx skills add synaptent/aragora --skill consult-fable
Clone the repo
git clone --depth 1 https://github.com/synaptent/aragora

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for consult-fable

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptent/aragora/consult-fable.svg)](https://agentmods.dev/skills/synaptent/aragora/consult-fable)
Your own site
<a href="https://agentmods.dev/skills/synaptent/aragora/consult-fable"><img src="https://agentmods.dev/badge/skills/synaptent/aragora/consult-fable.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01543
Opus 5 $0.00063 $0.00772
Sonnet 5 $0.00025 $0.00309
Haiku 4.5 $0.00013 $0.00154

Measured 5d ago against content hash 0ef5e4cfdec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

consult-fable 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.

.agents/skills/consult-fable/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consult Fable (bounded Claude Fable 5 advisory)

Ask Claude Fable 5 a question and get an answer back through bounded backend attempts. This replaces ad-hoc timeout 120 claude -p "..." calls, which hang or expire with no output. The default backend order is claude-fable-5 then claude-opus-5 through the local claude CLI. CLI attempts pass the prompt via stdin and use an empty MCP configuration. Explicit ARAGORA_MODEL_TRANSPORT=vibeproxy-prefer tries those exact models through VibeProxy before the CLI; vibeproxy-required fails closed instead of using CLI or paid API fallbacks.

--timeout is the maximum for one backend attempt. By default, the total consult budget is derived from every enabled attempt, so a full-timeout VibeProxy attempt cannot consume the CLI fallback budget. Pass --overall-timeout to set an explicit cap shared across all attempts. Prompts from inline args, --prompt-file, and stdin are capped at 512 KiB and are rejected before any backend attempt, so oversized context cannot silently burn API tokens when --api-fallback is enabled. The cap also applies to programmatic consult() calls after any --system/system preamble is combined with the user prompt.

API fallback is off by default because it can consume Anthropic API credits or billing when ANTHROPIC_API_KEY or aragora secrets are configured. Use --api-fallback only when paid API fallback is acceptable; unsupported CLI-only model ids such as claude-fable-5 are skipped for direct API calls. If no API key is available, the API backend records a normal failed attempt in the JSON envelope instead of being omitted.

How to invoke

From the repo root (any worktree):

# Inline question, defaults: model claude-fable-5, timeout 600s per attempt
# Default total budget is timeout multiplied by enabled backend attempts.
python3 scripts/consult_claude.py "One-paragraph question with the live state inlined."

# Long prompt from a file, machine-readable result
python3 scripts/consult_claude.py --prompt-file /tmp/question.md --json

# Require the local proxy and prohibit transport fallback
ARAGORA_MODEL_TRANSPORT=vibeproxy-required \
  python3 scripts/consult_claude.py --json "Reply with exactly READY"

# Prefer the local proxy, then fall back to the default CLI path
ARAGORA_MODEL_TRANSPORT=vibeproxy-prefer \
  python3 scripts/consult_claude.py --json "Reply with exactly READY"

# Bigger total budget for a hard question
python3 scripts/consult_claude.py --timeout 300 --overall-timeout 1200 --prompt-file /tmp/question.md

# Explicit paid API fallback after CLI attempts fail
python3 scripts/consult_claude.py --api-fallback --prompt-file /tmp/question.md

Read the full file on GitHub · 116 lines

Changes

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.

  1. 5d ago First seen · 116 lines · 126 tokens per session scan A 0ef5e4cfdec0

Subscribe to this mod's changes

consult-fable is a skill published in the GitHub repository synaptent/aragora (11 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,543 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens