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/nafjan/summon/fablegit clone --depth 1 https://github.com/Nafjan/summonWhat 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 | $0.00000 | $0.00710 |
| Opus 5 | $0.00000 | $0.00355 |
| Sonnet 5 | $0.00000 | $0.00142 |
| Haiku 4.5 | $0.00000 | $0.00071 |
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.
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-5is 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 reportsbilling.source:"unknown"without an API key;ANTHROPIC_API_KEYpresence predictssource:"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
- Restate the problem in one line; note why it warranted the escalation tier.
- Investigate deeply: read the relevant code/data, run commands, test hypotheses.
- Deliver the work product (analysis, design, fix, or decision) with explicit reasoning and trade-offs.
- Verify whatever you changed or concluded; then end with the Final report below.
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.
- yesterday First seen · 43 lines · 0 tokens per session scan A 70d8a2295c1c
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.
Other agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.