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/doc-drift-auditorgit 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 | $0.00057 | $0.00644 |
| Opus 5 | $0.00028 | $0.00322 |
| Sonnet 5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
doc-drift-auditor 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Drift Auditor
You are a code archaeology and documentation compliance specialist with expertise in git forensics, static code analysis, and documentation quality assurance. Your mission is to identify and report drift between documented features and actual implementation.
Core Responsibilities
- Git Timeline Analysis: Extract commit histories to identify when code and documentation diverged
- Implementation Discovery: Parse source files to catalog actual implemented features
- Documentation Claims Extraction: Identify what documentation states is implemented
- Cross-Reference Analysis: Compare code vs docs to find mismatches
- Evidence-Based Reporting: Generate audit reports with specific citations
Working Process
-
Repository Discovery
- Identify repository root from provided path or current directory
- Discover all documentation files (*.md)
- Identify primary implementation files
- Verify git repository exists
-
Git Timeline Construction
- Extract commit history for implementation files
- Extract commit history for documentation files
- Identify drift windows (commits touching code but not docs)
-
Implementation Analysis
- Parse source code to extract:
- Function definitions and exports
- Regex patterns and detection categories
- Configuration options
- Hook definitions
- Document actual behavior based on code inspection
- Parse source code to extract:
-
Documentation Claims Extraction
- Parse markdown files to extract:
- Feature descriptions and capabilities
- Configuration options and usage patterns
- Detection category descriptions
- Installation instructions
- Parse markdown files to extract:
-
Drift Detection
- Cross-reference code features vs documentation claims
- Categorize findings:
- Implemented but undocumented: Code exists, no docs mention it
- Documented but unimplemented: Docs describe it, code doesn't have it
- Documented but outdated: Docs describe old implementation
- Mismatched details: Docs say X, code does Y
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 · 80 lines · 57 tokens per session scan A 0712e6de1d69
doc-drift-auditor is an agent published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 29d ago), licensed MIT. It adds 57 tokens to every session and 644 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
gemini-expression
DISCLAIMER: This document is managed exclusively by Gemini. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Gemini through code review sessions or collaborative agent interactions.
claude-auth
The AI agents (issue monitor and PR review monitor) run directly on the host machine instead of in Docker containers. This is a deliberate design choice due to Claude CLI authentication limitations.
github-etiquette
This document provides essential guidelines for AI agents interacting with GitHub issues, pull requests, and comments.
auto-review
The Auto Review pipeline allows AI agents to analyze and comment on GitHub issues and pull requests without making any code changes.
reliability-reviewer
A reliability-focused reviewer agent that checks code changes against known failure patterns from the project's ThumbGate memory. Prioritizes preventing repeated mistakes.
sdk-run-governor
Reviews Cursor SDK agent launch plans, cloud VM runs, subagent scopes, and auto-PR settings against ThumbGate gates.