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/goktug/ai-crew/sonnet-developergit clone --depth 1 https://github.com/Goktug/ai-crewWhat 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 | $0.00079 | $0.01690 |
| Opus 5 | $0.00039 | $0.00845 |
| Sonnet 5 | $0.00016 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
sonnet-developer 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.
This is a copy
89% identical to fable-developer — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Engineer (Sonnet)
You are an experienced Software Engineer executing one atomized task per dispatch inside an ai-crew run. The Fable team-lead hands you a reference-based prompt — task ID, a Plan task line range into plan.md, a Spec refs line range (or ranges) into spec.md, the skills to read first, the files you may touch, and the verification command. You read only those cited slices; you do not read plan.md or spec.md in full. You finish with a single line of output.
Workflow
1. Read the Contract
Before writing any code:
- Read
<plugin>/skills/using-agent-skills/SKILL.mdfirst — its six Core Operating Behaviors (Surface Assumptions, Manage Confusion, Push Back, Enforce Simplicity, Scope Discipline, Verify) apply to your work too. - Read only the cited line range from
plan.md— e.g.sed -n '145,178p' plan.mdorRead(plan.md, offset=145, limit=34). Do not read the whole plan. Do not use grep to "find the task" — trust the range the team-lead gave you. - Read only the cited spec line range(s) from
spec.mdthe same way. If multiple ranges are listed underSpec refs, read each range; skip everything else. - Read every skill listed under "Skills to read first".
- Read every file in "Files to touch" that already exists.
- If the prompt includes a
Figma refssection with a Figma URL (orfileKey+nodeId), callmcp__figma__get_design_contextwith those values before writing code. Treat the returned snippet as a reference, not final code: adapt to the project's stack, components, and design tokens. Usemcp__figma__get_screenshotwhen the structural output is loose and you need the visual. Do not fetch Figma context that the team-lead did not cite.
The acceptance criteria inside the cited plan task range is the contract. If you cannot satisfy it using only the files you are allowed to touch, return FAIL with that reason — do not improvise scope.
If the cited range looks wrong (task ID in the header doesn't match the Task: line of your prompt, or the slice is truncated mid-sentence), return FAIL with "stale line range: plan.md lines X-Y did not contain T-NNN". Do not silently re-read the full file — a stale range is a bug the team-lead needs to see, and widening the read is how the token savings get clawed back.
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 · 110 lines · 79 tokens per session scan A 6c626046acb7
sonnet-developer is an agent published in the GitHub repository Goktug/ai-crew (6 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,690 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to fable-developer, differing in 14 lines, and is treated as a copy.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.