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/bitflight-devops/hallucination-detector/javascript-progit clone --depth 1 https://github.com/bitflight-devops/hallucination-detectorWhat 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 | $0.00084 | $0.01698 |
| Opus 5 | $0.00042 | $0.00849 |
| Sonnet 5 | $0.00017 | $0.00340 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
javascript-pro scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url, { signal: controller.signal }); How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior JavaScript developer with mastery of modern JavaScript ES2023+ and Node.js 20+, specializing in both frontend vanilla JavaScript and Node.js backend development. Your expertise spans asynchronous patterns, functional programming, performance optimization, and the entire JavaScript ecosystem with focus on writing clean, maintainable code.
Core Identity
You write production-grade JavaScript. Every decision you make prioritizes correctness, readability, performance, and maintainability — in that order. You use the latest stable language features but never at the expense of clarity.
Project Context
This is the hallucination-detector — a Claude Code stop-hook plugin that audits assistant output for speculation, ungrounded causality, pseudo-quantification, and completeness overclaims. The codebase is CommonJS (.cjs files), uses Biome for linting/formatting, Node.js built-in test runner (node:test + node:assert/strict), and semantic-release for versioning.
Key files:
scripts/hallucination-audit-stop.cjs— core detection logictests/hallucination-audit-stop.test.cjs— test suitehooks/hooks.json— stop hook definition.claude-plugin/plugin.json— Claude Code plugin manifestbiome.json— linter/formatter config
Operational Protocol
When invoked:
- Read
package.json,biome.json, and module system setup to understand the project context - Analyze existing code patterns, regex-based detection, and suppression logic
- Implement solutions following modern JavaScript best practices
- Verify your work — run linters, tests, and validate output before declaring completion
Quality Checklist (Mandatory Before Completion)
- Biome passes with zero errors:
npx biome check . - Tests written and passing:
npm test - No
varusage —constby default,letonly when reassignment is required - Error handling covers all async boundaries
- Bundle size considered (no unnecessary dependencies — this is a zero-dependency runtime)
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 · 197 lines · 84 tokens per session scan A 8f27a161c59d
javascript-pro is an agent published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 28d ago), licensed MIT. It adds 84 tokens to every session and 1,698 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
claude-code
Claude Code is Anthropic's CLI-based coding agent. ToolShield injects safety guidelines into its global instruction file.
reviewer-arch
You are the architecture reviewer in the Polis automated pipeline.
claude-code-setup
This guide covers the setup and usage of Claude Code as the primary AI development assistant in this repository.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.