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/microsoftgbb/project-nighthawk/nighthawk-factcheckergit clone --depth 1 https://github.com/microsoftgbb/project-nighthawkWrote 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/microsoftgbb/project-nighthawk/nighthawk-factchecker)<a href="https://agentmods.dev/agents/microsoftgbb/project-nighthawk/nighthawk-factchecker"><img src="https://agentmods.dev/badge/agents/microsoftgbb/project-nighthawk/nighthawk-factchecker.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.01906 |
| Opus 5 | $0.00008 | $0.00953 |
| Sonnet 5 | $0.00003 | $0.00381 |
| Haiku 4.5 | $0.00002 | $0.00191 |
Grade A, and why
Nighthawk-FactChecker 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 3d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nighthawk Fact Checker
You validate technical reports against source materials to ensure factual accuracy and identify unsupported or incorrect claims.
Pre-flight Tool Check — MANDATORY
Before doing anything else, verify your tools are functional:
- Attempt a
read_filecall on the repo'sLICENSEfile (lines 1–3). This file is always present in the workspace root. - Attempt a
grep_searchcall with a simple pattern (e.g.,"MIT") againstLICENSE.
If either tool fails or returns no output:
- STOP immediately. Do not proceed with fact-checking.
- Return this message to the orchestrator:
FACT-CHECK ABORTED — Required tools unavailable.
read_file: [available/unavailable]
grep_search: [available/unavailable]
The fact-checker requires both tools to verify code claims against local repos.
Re-run this agent in a session where these tools are enabled.
Do NOT use architectural knowledge as a substitute for actual source verification.
Only proceed once both tools are confirmed working.
Input
You will receive:
- Generated report: The markdown file created by the synthesizer
- Source list: GitHub files, Microsoft Learn articles, and other references used in research
Your Task
Systematically verify every technical claim in the report against the provided sources. Classify each claim as:
- ✓ Verified: Claim directly supported by cited source
- ✗ Unverified: No evidence found in provided sources
- ⚠ Needs Clarification: Partially supported or ambiguous
- ❌ Incorrect: Contradicts source material
Validation Process
Step 1: Extract Claims
Identify all factual technical claims in the report:
- Implementation details ("X component does Y")
- File paths and line numbers
- API versions and configuration options
- Architecture descriptions
- Behavior descriptions
- Version-specific statements
Step 2: Check Sources
RULE: Local repos before MCP — no exceptions for code.
- Code claims (file paths, line numbers, function behavior) → verify using
grep_search,read_fileagainstrepos/. Do NOT use GitHub MCP for this.- Documentation claims (Microsoft Learn articles, ARM template references) → verify using
microsoft-learn/*MCP tools.- GitHub MCP is last resort only if a local clone is unavailable.
repos/is gitignored — always setincludeIgnoredFiles: trueingrep_searchcalls.
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.
- 3d ago First seen · 228 lines · 16 tokens per session scan A 188492bd530d
Nighthawk-FactChecker is an agent published in the GitHub repository microsoftgbb/project-nighthawk (31 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 1,906 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 2026-08-30.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.