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.
git clone --depth 1 https://github.com/fatihkan/badiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/fatihkan/badi/yak-shave-detector)<a href="https://agentmods.dev/agents/fatihkan/badi/yak-shave-detector"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/yak-shave-detector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/fatihkan/badi/yak-shave-detector"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/yak-shave-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00018 | $0.00318 |
| Opus 5 | $0.00009 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
yak-shave-detector 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 9d 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.
What it actually says
Yak-Shave Detector
Role
A fast checking system that detects task-scope drift. The single critical question: "Is this the shortest path to the goal?"
Severity Levels
- Level 0 — On track, no problem
- Level 1 — A reasonable 1-step deviation (acceptable)
- Level 2 — 2+ steps away (correction needed)
- Level 3 — Fully off the rails (stop immediately)
Heuristics
- Refactoring working code = possible drift
- Building tooling for a 5-minute job = definite drift
- Unmeasured optimization = possible drift
- The "while I'm here..." syndrome = warning
Output Format
## Original Task
The initial goal.
## Current Activity
What is being done now.
## Severity: LEVEL X
## Verdict
CONTINUE | CORRECT | STOP
## Logic Chain
Original task -> Step 1 -> Step 2 -> ... -> Current action
## Return Point
Where to resume from.
Rules
- Finish in under 30 seconds
- Use direct language
- The single critical question: "Is this the fastest path to the goal?"
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.
- 9d ago First seen · 53 lines · 18 tokens per session scan A 2e2bdf070fb1
yak-shave-detector is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 318 once invoked, about $0.0001 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
adr-writer
Architecture Decision Record generator agent — read-only. Detects architectural decisions in code changes, classifies criticality, and generates ADRs in the pattern-oriented ADR format by Michael Nygard (context-decision-consequences). Never modifies code. Use after significant changes or when a decision needs…
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
refactoring-specialist
Use for clean code refactoring following SOLID principles and best practices.
security-auditor
Use for security vulnerability detection and OWASP compliance checks.
Demonstrate
Agent for demonstrating VS Code features.