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/marcomuser/conformal/agents-mdgit clone --depth 1 https://github.com/marcomuser/conformalWhat 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 | $0.00669 | $0.00669 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
conformal 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 today.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conformal — AGENTS.md
Agent-focused notes for safe, fast contributions. Format reference: agents.md.
Setup
npm i
npm run typecheck
npm run test
Examples:
cd examples/react && npm i && npm run dev
cd examples/svelte && npm i && npm run dev
Public API
conformal:getPath,setPath,decode,parseFormData,serialize,coerceString,coerceNumber,coerceBigint,coerceBoolean,coerceDate,coerceFile,coerceArray; types:PathsFromObject,Submissionconformal/valibot:coerceString,coerceNumber,coerceBoolean,coerceDate,coerceBigint,coerceFile,coerceArray(experimental)conformal/zod:string,number,boolean,date,bigint,enum,file,url,email,object,array(deprecated)
Exports live in src/index.ts, src/valibot/index.ts, and src/zod/index.ts.
Non‑negotiable invariants
parseFormDatais synchronous; throwTypeError("Schema validation must be synchronous")if schema returns a Promise.setPath/getPathare immutable and prototype‑safe (block__proto__,constructor.prototype); support nested arrays/objects and sparse indices.Submissionalways includesinput; separatefieldErrors(dot/bracket paths, numeric indices in brackets) fromformErrors.serialize: number/bigint →.toString(), boolean →"on"/""(configurable),Date→ ISO via.toISOString().- Types
InputValue<T>andPathsFromObject<T>must remain correct for nested structures and browser types.
Code style
- TypeScript strict mode (see
tsconfig.jsonflags). - ESM-only, isomorphic runtime (no Node-only APIs).
- Prettier formatting:
npm run format:write. - Keep runtime deps minimal;
valibotis an optional peer dependency.
Build & test
# Fast local CI
npm run format:check && npm run typecheck && npm run test
# Focus tests
npx vitest run -t "<name>" # by test name
npx vitest run test/parse.test.ts
Quick playbooks
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.
- today First seen · 59 lines · 669 tokens per session scan A 2aa266584503
conformal AGENTS.md is an instructions file published in the GitHub repository marcomuser/conformal (39 stars, last pushed 10mo ago), licensed MIT. It adds 669 tokens to every session, about $0.0033 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 2026-09-01.
Other instructions, from other repositories
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
Instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
walkerOS CLAUDE.md
Instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.
huly-mcp CLAUDE.md
Instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.
movi-player AGENTS.md
Instructions for MrUjjwalG/movi-player, covering agents.md — movi-player for ai coding assistants, 1. what this is, 2. package entry points, 3. architecture map and 4. the web component .
sofagent GEMINI.md
Instructions for KongFangXun/sofagent, covering gemini.md · sofagent gemini cli 适配(薄挂载), 会话开始时按序加载(四层加载链), 审计强制(平台无关) and 连接 mcp server.