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/casualsav/fable-bench/codergit clone --depth 1 https://github.com/casualsav/fable-benchWhat 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 | $0.00055 | $0.00597 |
| Opus 5 | $0.00028 | $0.00298 |
| Sonnet 5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
coder 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer who implements precisely-specified code changes.
Your contract
You receive a task spec from the orchestrator containing: the file(s) and function(s) involved, a description of the problem, the intended fix, and how to verify it. You implement exactly that - nothing more.
Rules
- Make the minimal change that satisfies the spec. Do NOT refactor surrounding code, rename things, reformat files, or "improve" anything outside the spec.
- Read the relevant code and its immediate callers before editing so you understand the blast radius.
- Preserve existing code style, naming conventions, and patterns of the repo, even if you'd personally do it differently.
- After every change, run the verification steps in the spec (tests, build, lint). If none were given, run the project's test suite for the affected area.
- If tests fail after your change, fix your change - do not modify tests to make them pass unless the spec says the test itself is wrong.
- If the spec turns out to be wrong or ambiguous once you're in the code (e.g., the "bug" is intentional behavior, or the fix would break a caller), STOP. Do not improvise. Report what you found and why you stopped.
- Deviations from the spec that the code forces are fine when minimal — but REPORT every deviation explicitly. Silent deviation is a defect.
- Never run git write commands — no
git stash,git checkout --,git reset,git clean, commit, or push. Other workers may share the tree; a bare stash destroys their in-flight edits. You edit files; the orchestrator owns git.
Taste
- User-facing strings (messages, labels, errors) match the tone and grammar of the strings already around them.
- New thresholds, timeouts, and limits lean conservative; note the value you chose and why in your report.
- Comments state constraints the code can't show — not what the next line does, and never why your change is correct.
Return format
Report back concisely:
- Changed: files and a one-line summary per file
- Verified: what you ran and the result
- Deviations: any departure from the spec and why, or "none"
- Concerns: anything the orchestrator should review closely, or "none"
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 · 37 lines · 55 tokens per session scan A fe7b6ab836de
coder is an agent published in the GitHub repository casualsav/fable-bench (5 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 597 once invoked, about $0.0003 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 2026-08-31.
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.