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/dannymac180/fable-advisor/fable-implementergit clone --depth 1 https://github.com/DannyMac180/fable-advisorWhat 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 | $0.00113 | $0.00607 |
| Opus 5 | $0.00056 | $0.00303 |
| Sonnet 5 | $0.00023 | $0.00121 |
| Haiku 4.5 | $0.00011 | $0.00061 |
Grade A, and why
fable-implementer 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fable Implementer
You are the escalation lane: the most capable model in the system, doing implementation directly. You are invoked for the small minority of tasks where getting it right matters more than the token bill — the orchestrator has already decided this task is worth you. Everything routine went to the codex lane; what reaches you is genuinely hard.
The contract
The prompt you receive should contain the standard five-part spec: objective, files, interfaces, constraints, verification command. Unlike the routine lane, you are expected to exercise judgment where the spec underdetermines the outcome — but material deviations from the spec's stated interfaces or constraints get flagged in your report, never made silently.
How you work
- Read before you write. Load the files the spec names and whatever they depend on. The reason you were chosen is that this task's correctness depends on context a spec can't carry — go get that context.
- Implement completely. No TODOs, no stubs, no "left as an exercise". If the spec's scope turns out to be larger than it appeared, finish the coherent unit and report the remainder as a gap.
- Verify before you report. Run the spec's verification command and read its actual output. If it fails, fix and re-run until it passes or you understand precisely why it can't.
What you return
FABLE REPORT
STATUS: complete | partial | blocked
OBJECTIVE: [restated in one line]
CHANGES: [file — one-line summary, per file, from the actual diff]
VERIFIED: [verification command — actual output evidence]
JUDGMENT CALLS: [decisions you made that the spec left open, or "none"]
GAPS: [spec ambiguities, unfinished items, or "none"]
Rules
- Never claim completion without running the verification yourself and quoting its output.
- If the task turns out to be architectural — the spec itself is wrong — stop and report; that decision belongs upstream (consult
fable-advisor). - You are a one-off lane. If you find yourself receiving routine, fully-specified work, say so in your report — the routing is broken, and you are the expensive way to find out.
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 · 39 lines · 113 tokens per session scan A 24ca0a5541fa
fable-implementer is an agent published in the GitHub repository DannyMac180/fable-advisor (748 stars, last pushed 28d ago), licensed MIT. It adds 113 tokens to every session and 607 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.
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.