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/layzeedk/angular-typechecker/agents-mdgit clone --depth 1 https://github.com/LayZeeDK/angular-typecheckerWhat 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 | $0.08966 | $0.08966 |
| Opus 5 | $0.04483 | $0.04483 |
| Sonnet 5 | $0.01793 | $0.01793 |
| Haiku 4.5 | $0.00897 | $0.00897 |
Grade C, and why
angular-typechecker AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
the wrong tree. NEVER `rm -rf node_modules` and never run a RECURSIVE delete on a worktree How it starts
The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md -- angular-typechecker
Agent-agnostic instructions for any AI coding agent working in this repository.
(Claude Code loads this via the @AGENTS.md reference at the top of CLAUDE.md.)
Changing this file
Any change to AGENTS.md MUST be code-reviewed. This file governs how every AI agent
works in this repository, so an inaccurate, ambiguous, or unverified instruction propagates
silently into all future agent behavior. The review may be satisfied EITHER by an explicit
independent review before commit, OR by the mandatory /gsd-code-review step that runs
during phase execution (the code_review_gate), which reviews every source file changed in
the phase -- including this one. Either way, an AGENTS.md change is not "done" until a
code review has checked it for factual accuracy against the actual codebase and tooling,
clarity, and internal consistency, and every finding is resolved. (This rule exists because
a release-mechanics claim in this file was once wrong about the 0.x semver bump shift and
about --skip-publish semantics -- review is what caught both.)
Conventional Commits drive the changelog and the released version
This repository releases angular-typechecker to npm with nx release configured
for version.conventionalCommits: true (see nx.json -> release). That means the
NEXT version number AND the generated changelog are computed from the commit log --
not chosen by hand. Every commit you write is release input. Follow these rules so the
release machinery behaves predictably.
Commit message format
type(scope): short imperative description
optional body explaining what and why
optional footer (e.g. BREAKING CHANGE: ..., Refs: ...)
typeis required and lowercase.scopeis optional but, when present, is rendered verbatim in the changelog (see the scope-hygiene rule below).- A breaking change is marked EITHER by a
!before the colon (feat(core)!: ...) OR by aBREAKING CHANGE:footer.
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 · 512 lines · 8,966 tokens per session scan C 9a8841a0def1
angular-typechecker AGENTS.md is an instructions file published in the GitHub repository LayZeeDK/angular-typechecker (10 stars, last pushed 23d ago), licensed MIT. It adds 8,966 tokens to every session, about $0.0448 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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 AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.