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/tao-io/foldcase/agents-mdgit clone --depth 1 https://github.com/tao-io/foldcaseWhat 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 | $0.02329 | $0.02329 |
| Opus 5 | $0.01164 | $0.01164 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
foldcase 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 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.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working rules — Foldcase
Binding for humans and agents. Short on purpose. The reasoning lives in
docs/adr/; this file is the rules that follow from it.
The stack is fixed
- Bun is the development toolchain: the package manager, the test runner, and the
version
misepins. Not npm, not pnpm, not turbo. Vite builds one thing and one thing only — the documentation site underdocs/site/, by declared exception (ADR-0003). - Node and Bun both run the shipped tool. The core is runtime-agnostic Effect and each
runtime gets one thin shell —
src/main.ts(Node) andsrc/main.bun.ts(Bun). A shell binds a runtime, hands the programprocess.argv, and writes back the exit code; anything else in a shell is a bug. See ADR-0002 › Amendment 1. - The build is
tsc -b, and there is no bundler.mise run buildcompilessrc/todist/— one.jsand one.d.tsper source file — and copies the coverage collector beside its caller.bun build --compileis not used and is not coming back: a compiled binary resolvesimport(path)inside its own/$bunfs, so it could never load an external*.showcase.ts, which is the whole job. - Effect v4 for all non-trivial logic: typed errors, Layers,
Schemafor every contract. Not bareasync/throw. Effect is a peer dependency — never promote it to a hard dependency, or a consumer ends up with two Effect instances. Both@effect/platform-*packages are optional peers: a consumer needs only the one their shell runs, and the library entry points need neither. - Foldkit is the only framework this line supports. No React, no Solid, no Vue, no Svelte — not in source, not in tests, not in devDependencies.
- No CSF-3. No
Meta, noStoryObj, noexport default meta, no*.stories.ts. A catalog isexport const showcases: ReadonlyArray<Showcase>in a*.showcase.tsfile. - TypeScript only under
src/. The single exception issrc/coverage/collector.mjs, the Node V8 coverage instrument, which is allowlisted by name in the stack gate. docs/site/is the documentation site, a foldocs (Foldkit) application that Vite builds andmise run docs:builddrives. It is the one place a bundler runs. Its pages are derived fromREADME.md,CHANGELOG.mdanddocs/adr/on every build and are gitignored, so the prose has exactly one home. Nothing there touchessrc/,dist/or the tarball. See ADR-0003.
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 · 151 lines · 2,329 tokens per session scan A 6bed8e81ed3c
foldcase AGENTS.md is an instructions file published in the GitHub repository tao-io/foldcase (1 stars, last pushed 28d ago), licensed MIT. It adds 2,329 tokens to every session, about $0.0116 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.