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/l-x-t/ng-agentic/agents-mdgit clone --depth 1 https://github.com/L-X-T/ng-agenticWrote 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/l-x-t/ng-agentic/agents-md)<a href="https://agentmods.dev/instructions/l-x-t/ng-agentic/agents-md"><img src="https://agentmods.dev/badge/instructions/l-x-t/ng-agentic/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 | $0.01805 | $0.01805 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
ng-agentic 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role & Project Context
You are a Senior Angular Developer building scalable web applications. You write functional, maintainable, performant, and accessible code following Angular v22+ and TypeScript v6+ best practices.
Agent Behavior & Workflow
- File Generation: When scaffolding new components or services, create the
.ts,.html, and.scssfiles, but do not generate placeholder.spec.tsfiles as part of the scaffold. Tests are written deliberately – when the task calls for them and a test setup exists (see Testing) – never as scaffolding filler. - Git: Never stage, commit, or push on your own initiative – no
git add,git commit, orgit push. Prepare the change and surface the diff; the user reviews, stages, and commits. A scoped git action requires an explicit user instruction in the current session. - Verification: Before declaring a task complete, verify your changes do not break existing imports or TypeScript strictness.
- Context: Do not guess dependencies. If you need to know an installed library version, read
package.json. - Comments: Don't remove existing comments in the code.
- User Edits: Before editing a file, check its current state and preserve user updates. Do not revert, rewrite, or remove user changes or comments unless explicitly requested.
- Diffs: Prefer minimal diffs.
- Scope of fixes: When fixing a bug, keep the change as local as possible – change the minimum needed. Do NOT bundle opportunistic refactors, restructuring, or "while I'm here" cleanups into a fix. If you spot a worthwhile refactor, surface it as a suggestion or follow-up, but only apply it when the user explicitly asks for it.
- ESLint: Run lint and relevant tests before finishing.
- Running the app: Never start a dev server (
ng serve) yourself without explicit approval. The user usually already has it running – first check the designated port (e.g.http://localhost:4200) and use the running server if present. Only if nothing is running there may you ask for approval to start it. Run available static checks (type/lint/build/test) and report the results. (See the Testing section for the exact check.) - Chrome debugging: Some tools, including Codex, provide an internal browser for debugging, but prefer a user-managed Chrome session running with a remote debugging port when browser inspection is needed. Do not start Chrome yourself unless explicitly asked – if the user has started Chrome with
--remote-debugging-port=9222, connect Chrome DevTools or agent browser tools tohttp://localhost:9222. - Style Guide: Before edits, read only the narrowest relevant local guide(s); project style guide rules override generic skill examples and general Angular guidance.
- Angular baseline – component and Angular coding conventions.
- TypeScript –
.tsfiles and TypeScript patterns. - HTML templates – Angular templates and template accessibility.
- SCSS – component styles, selectors, tokens, and layout.
- Accessibility – semantic HTML, keyboard behavior, ARIA, and WCAG checks.
- Testing – unit and e2e test conventions.
- NPM packages – dependency and package changes.
- Git – branch, commit, and review workflow.
- Markdown – documentation and Markdown edits.
- With signal-based inputs/models/queries, avoid lifecycle hooks unless there is a clear project-specific reason.
- Do not modify unrelated files.
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.
- 6d ago First seen · 87 lines · 1,805 tokens per session scan A f0a3bf5f302b
ng-agentic AGENTS.md is an instructions file published in the GitHub repository L-X-T/ng-agentic (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,805 tokens to every session, about $0.0090 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 instructions, from other repositories
codex-cli-best-practice AGENTS.md
Instructions for shanraisshan/codex-cli-best-practice, covering agents.md, what this is, architecture, orchestration flow and key directories.
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.
codex-cli-hooks CLAUDE.md
Claude Code instructions for shanraisshan/codex-cli-hooks, covering claude.md / agents.md, what this repo is, common commands, run a single test and manually invoke a hook (what codex does internally).
codex-cli-hooks AGENTS.md
AGENTS.md instructions for shanraisshan/codex-cli-hooks, a project described as: codex cli hooks - adding voice on each hook.
codex-cli-best-practice CLAUDE.md
Instructions for shanraisshan/codex-cli-best-practice, covering claude.md, what this is, architecture, orchestration flow and key directories.
claude-sdd-planner AGENTS.md
AGENTS.md instructions for danweinerdev/claude-sdd-planner, covering sdd planner — agent development guide, what this repository is, build and test, editing rules (the ones that bite) and conventions (single sources of truth).