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/featuregit 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/feature)<a href="https://agentmods.dev/instructions/paruff/ufawkesai/feature"><img src="https://agentmods.dev/badge/instructions/paruff/ufawkesai/feature.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 | $0.00441 | $0.00441 |
| Opus 5 | $0.00220 | $0.00220 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
Feature Development Instructions 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.
What it actually says
Feature Development Instructions
The PM Issue Is Your Spec
When implementing a feature from a GitHub issue:
- Read the acceptance criteria first. Every acceptance criterion becomes either a unit test or a BDD scenario.
- Read the user story. Understand why this feature exists before writing any code.
- Check
docs/KNOWN_LIMITATIONS.mdfor any gotchas in the area you're working. - Write the failing test first. Commit it before writing implementation code.
Feature Development Sequence
1. Read the issue acceptance criteria
2. Identify which src/services/ functions are needed
3. Write unit test(s) for any new utility logic → commit: test(scope): failing test for [ISSUE-ID]
4. Implement the utility/service logic → commit: feat(scope): implement [ISSUE-ID]
5. Write/update the screen/component → commit: feat(ui): [ISSUE-ID] screen
6. Run: npm run preflight (lint + typecheck + tests must all pass)
7. Open draft PR with the required PR template filled out
Component Patterns
[PLACEHOLDER — Add your actual component patterns here. Example:]
// ✅ Correct — screen uses hook, hook calls service
export function GoalDetailScreen() {
const { goal, isLoading } = useGoal(goalId);
// ...
}
// ❌ Wrong — screen calls Firebase directly
export function GoalDetailScreen() {
const goal = await getDoc(doc(db, "goals", goalId)); // NEVER
}
When Something Is Ambiguous
If the issue acceptance criteria don't cover an edge case:
- Handle it defensively (validate input, show a user-friendly error)
- Add a comment:
// TODO: PM decision needed — [describe the ambiguity] - Flag it in the PR description under "Files I was NOT sure about"
Do NOT invent product decisions. Flag them.
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 · 56 lines · 441 tokens per session scan A cba71f5a3f0d
Feature Development Instructions is an instructions file published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 12d ago), licensed MIT. It adds 441 tokens to every session, about $0.0022 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
template CLAUDE.md
Claude Code instructions for docxology/template, covering claude.md, how this file fits with other entry points, quick reference, ci mirror (github actions) and common commands.
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.
trellis CLAUDE.md
Instructions for craigcossairt/trellis, a project described as: The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge…
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.