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 instructions/paruff/ufawkesai/agents-mdgit clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/instructions/paruff/ufawkesai/agents-md)<a href="https://agentmods.dev/instructions/paruff/ufawkesai/agents-md"><img src="https://agentmods.dev/badge/instructions/paruff/ufawkesai/agents-md.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 5.1 | $0.01376 | $0.01376 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
uFawkesAI AGENTS.md 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — uFawkesAI
TOKEN COST NOTICE: This file loads on EVERY Copilot/Claude Code/Cursor request. Every line here is billed on every interaction. Keep it lean. Full details live in
.agents/skills/— load them on demand only.
1. AI Policy
- AI agents implement. Humans decide.
- No AI-generated code merges without human review and approval.
- Use your agent's read-only/question mode for questions; reserve multi-file/agentic mode for multi-file tasks.
- Read
docs/MODEL_ROUTING_GUIDE.mdbefore choosing a model or mode. - GitHub Copilot users: read
docs/COPILOT_COST_GUIDE.mdto understand token cost before starting.
Data policy: No customer PII in AI prompts.
2. Project Identity
Product: uFawkesAI — Agent orchestration framework for platform engineering
Stack: TypeScript · Node 20 · GitHub Actions · OpenTelemetry
Key constraints: 7 core pipeline agents + 7 flow/meta agents (14 total, see .agents/README.md), 31 skill areas, humans = routing layer
3. Five Hard Rules (Never Violate)
- No secrets, API keys, or credentials in any file.
- No merging your own PR.
- No modifying
AGENTS.md— the source file. Its symlinked aliases (CLAUDE.md,.cursorrules,.github/copilot-instructions.md,.cursor/rules/AGENTS.md) always mirror it; edit the source only. - Run pre-commit hooks before committing (
pre-commit run --all-files). - All agent outputs must satisfy contracts in
.agents/assertions/minimal-report.yaml.
4. Token Budget Protocol
Before starting any task touching > 3 files:
- State scope in one sentence.
- List files you plan to read.
- Say: "Confirm I should proceed? (moderate/high credit cost)"
For questions → use your agent's read-only/question mode (60–90% cheaper than agentic mode).
5. Agent Routing
Invoke the most relevant agent directly:
| Task | Agent | Example |
|---|---|---|
| "Write requirements for..." | @spec |
"Write requirements for user authentication" |
| "Design architecture for..." | @design |
"Design architecture for payment processing" |
| "Implement feature X" | @build |
"Implement the login form component" |
| "Write tests for..." | @test |
"Write tests for the auth service" |
| "Run tests and check coverage" | @test-execution |
"Run all tests and report coverage" |
| "Review this PR" | @review |
"Review PR #42 for security and quality" |
| "Validate all outputs are consistent" | @cross-validation |
"Cross-validate spec, design, and build outputs" |
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 · 137 lines · 1,376 tokens per session scan A 4d4e4aaf5dfb
uFawkesAI AGENTS.md is an instructions file published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 13d ago), licensed MIT. It adds 1,376 tokens to every session, about $0.0069 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 2026-09-03.
Other instructions, from other repositories
LynxPrompt CLAUDE.md
Claude Code instructions for GeiserX/LynxPrompt, covering claude.md - ai agent instructions for lynxprompt, 🚀 release process (critical - read carefully), understanding the release pipeline, step-by-step release process and 1. switch to develop branch.
domain-experts AGENTS.md
AGENTS.md instructions for wonsukchoi/domain-experts, covering agent guide for this repo, what lives where, rules, release (npm) and known pitfalls.
skillcraft AGENTS.md
Instructions for cloudroad-io/skillcraft, covering skillcraft, install, or: pip install skillcraft, commands and how it works.
cursor-os AGENTS.md
Instructions for KingEmma7/cursor-os, covering agents.md — cursor-os, what this project is, repository layout, working agreements and verification before done.
agents-md AGENTS.md
Instructions for eugeniughelbur/agents-md, covering agents.md, commands, testing, project structure and code style & conventions.
vibeproof CLAUDE.md
Instructions for HumanDealer/vibeproof, covering claude.md — claude code operating contract, the non-negotiables, claude code specifics and the standard workflow.