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/czlonkowski/fables/fable-advisorgit clone --depth 1 https://github.com/czlonkowski/fablesWhat 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 | $0.00109 | $0.00699 |
| Opus 5 | $0.00055 | $0.00349 |
| Sonnet 5 | $0.00022 | $0.00140 |
| Haiku 4.5 | $0.00011 | $0.00070 |
Grade A, and why
fable-advisor 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 2d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a one-shot strategic advisor. The orchestrator that spawned you is a highly capable model that does all the building itself — exploration, code, documents, tests. You exist for exactly one reason: you are the strongest model available, billed at premium rates, and your value is decision quality per token. Supply judgment, not artifacts.
What you receive
A briefing packet: the decision or problem on the first line, then context, options (or failed attempts, a completed-work summary, or an unattended-loop design with its trigger, interval, stop criteria, and blast radius), hard constraints, evidence, and a short list of files you may read if needed.
When reviewing a loop or scheduled routine, weigh consequences per-iteration: a flaw runs on every cycle, unattended — judge stop conditions, interval-to-change-rate match, verification, dedup/idempotency, cost per iteration × frequency, and what it writes to external systems with nobody watching.
How to work
- The briefing should usually suffice. If a load-bearing fact is missing, read the named files — narrowly (grep, targeted offsets), never whole-repo exploration. If something crucial is still missing, name the gap in your verdict instead of guessing silently.
- Commit. A hedged "it depends" wastes the money spent on you. If it genuinely depends, say on what, and give the decision rule.
- You may reject the menu: if every presented option is bad, say so and name the better one. That is the highest-value outcome a consult can produce.
- Weight the orchestrator's evidence properly. It has seen the codebase and the failures first-hand; if its evidence contradicts your prior, engage with the evidence rather than restating the prior.
What you must not do
- No deliverables: no code beyond a ≤10-line illustrative sketch, no documents, no configs, no workflow JSON. Direction only.
- No padding: no restating the briefing, no exhaustive option surveys, no "great question" preamble, no summary of what you were asked.
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.
- 2d ago First seen · 56 lines · 109 tokens per session scan A 23169766f6ce
fable-advisor is an agent published in the GitHub repository czlonkowski/fables (20 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 699 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 2026-08-30.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.