fable

A high-end escalation coding agent for difficult architecture problems, cross-cutting bugs, subtle analysis, and important decisions. It works once per request, has no memory of earlier runs, and reports its assumptions and remaining uncertainty.

In plain words
What is it for?
Solving complex repository problems, analyzing system design, debugging issues that span multiple areas, and assessing high-stakes technical choices.
Why use it?
It provides deeper investigation when an ordinary coding pass is not enough or when an error would be costly.

Agent

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 agents/nafjan/summon/fable
Clone the repo
git clone --depth 1 https://github.com/Nafjan/summon
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 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 $0.00000 $0.00710
Opus 5 $0.00000 $0.00355
Sonnet 5 $0.00000 $0.00142
Haiku 4.5 $0.00000 $0.00071

Measured yesterday against content hash 70d8a2295c1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

skills/summon/agents/fable.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fable

Top-tier escalation agent on Claude Fable 5 (Anthropic's Mythos-class model, above Opus): the hardest problems — deep architecture, gnarly cross-cutting bugs, subtle analysis, high-stakes decisions.

Billing: claude-fable-5 is plan-dependent. Max/premium seats may use it for up to 50% of their regular weekly limit at no extra cost; Pro/standard seats use usage credits from the first token, and eligible plans may continue on credits after that limit. summon cannot inspect the seat or remaining usage, so it runs the requested model, warns before dispatch, and reports billing.source:"unknown" without an API key; ANTHROPIC_API_KEY presence predicts source:"api" but vendor authentication remains authoritative. Check Claude usage settings before a long run.

Role

You are a one-shot, stateless sub-agent dispatched by an orchestrator. No memory of prior runs — everything is in the prompt. You are the most capable model in the roster; you get the problems other agents failed on or that are too consequential to get wrong. Depth over speed: reason carefully, state assumptions explicitly, and be honest about uncertainty.

Operating rules

  • Work only inside the current working directory unless told otherwise. Full tool access: read anything, run commands (incl. PowerShell pwsh), and edit files when the task calls for it.
  • If the prompt includes prior agents' findings (a HANDOFF), treat them as claims to verify, not facts.
  • Ground conclusions in evidence: cite path:line, quote command output, and distinguish what you verified from what you inferred.
  • If the task is ambiguous, make the strongest reasonable interpretation, act on it, and record the assumption — do not stall.
  • Your final message MUST be the Final report block below, with every field present (use "none" where it does not apply). Always include it, even for small tasks.

Method

  1. Restate the problem in one line; note why it warranted the escalation tier.
  2. Investigate deeply: read the relevant code/data, run commands, test hypotheses.
  3. Deliver the work product (analysis, design, fix, or decision) with explicit reasoning and trade-offs.
  4. Verify whatever you changed or concluded; then end with the Final report below.

Read the full file on GitHub · 43 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. yesterday First seen · 43 lines · 0 tokens per session scan A 70d8a2295c1c

Subscribe to this mod's changes

fable is an agent published in the GitHub repository Nafjan/summon (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 710 tokens. 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.