Borrowing it
Nothing to install: this file belongs to MiaoDX/intuitive-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MiaoDX/intuitive-flow/main/AGENTS.mdgit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote 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/miaodx/intuitive-flow/agents-md)<a href="https://agentmods.dev/instructions/miaodx/intuitive-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/miaodx/intuitive-flow/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/miaodx/intuitive-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/miaodx/intuitive-flow/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00527 | $0.00527 |
| Opus 5.5 | $0.00211 | $0.00211 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
intuitive-flow 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 16d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
- Repo-owned skill sources live in
skills/; update installed copies through the sync script. - Use Bash for orchestration and Bun-run TypeScript for structured scripts. For Python, use
uvand the repository.venv; avoid unnecessary dependencies. - For web retrieval, use
fetchMCP for simple direct reads, Firecrawl for general external pages, and Jina Reader as fallback; follow the retrieval reference. - Fail explicitly in code; avoid
hasattr()/getattr()for known types. - Prefer live-at-HEAD behavior and forward migrations; remove obsolete in-repo APIs and shims unless a bridge is explicitly required.
- Keep commits atomic with a
Co-authored-by:trailer naming the agent that did the work (for exampleCodex <[email protected]>). Do not amend or force-push unless asked; fetch and rebase if a push is rejected because the remote moved. - Explicit user instructions take precedence over skill instructions. If a skill would make you pause, ask, or stop short of the request, name the
SKILL.mdand quote the instruction. bun run verifychecks the repo.scripts/update.shmutates installed tools and user configuration; it is not a test command.
Task routing
- Use
$intuitive-flowfor ordinary execution,$intuitive-reduce-entropyfor unknown cleanup targets, and$intuitive-refactorfor selected seams. - Use
$intuitive-preflightfor unresolved scope or acceptance decisions; reuse the user's existing authorization. - Guidance/setup belongs to
$intuitive-init, human docs to$intuitive-doc, test-suite organization to$intuitive-tests, and requested history cleanup to$intuitive-squash. - For delegation, read
skills/_shared/references/delegation.md; assign disjoint ownership and keep integration and verification in the main session.
Sources of truth
- Keep README thin. Use ARCHITECTURE for boundaries, STATUS for current commands/state, and
docs/human/**for detail, as the task requires. .planning/holds locked summaries and execution state; archives, generated release notes, and unpromoted specs are historical. Prefer curated planning ingest.- Update the owning human doc when runtime truth changes, and active planning summaries when scope or decisions change.
- Shared rules belong here; CLAUDE.md contains Claude-specific additions. Put reusable procedures in skills and deterministic rules in scripts/hooks.
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.
- 16d ago Changed · +15 tokens per session 725ea2e3b2c1
- 1mo ago Changed · +2 lines · +66 tokens per session f05167e4fe9e
- 1mo ago Changed · +4 tokens per session e84af60fff79
- 1mo ago Changed · -61 lines · -1,001 tokens per session 1fddb6ece02e
- 1mo ago Changed · +12 tokens per session d1d76e3ac6da
- 1mo ago First seen · 84 lines · 1,431 tokens per session scan A 2b46cd77dd11
intuitive-flow AGENTS.md is an instructions file published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 17d ago), licensed MIT. It adds 527 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-08-30.
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.