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/jo-duchan/tapflow/agents-mdgit clone --depth 1 https://github.com/jo-duchan/tapflowWhat 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 | $0.04896 | $0.04896 |
| Opus 5 | $0.02448 | $0.02448 |
| Sonnet 5 | $0.00979 | $0.00979 |
| Haiku 4.5 | $0.00490 | $0.00490 |
Grade A, and why
tapflow 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tapflow — AGENTS.md (Common Rules)
Package-specific rules are referenced via INDEX.md.
WHAT
tapflow is an open-source self-hosted library that lets the entire team — PO, PM, designers, backend engineers, and QA — test iOS/Android apps directly from a browser. It uses the Mac you already own — no external cloud dependency.
Core value
Remove friction. Anyone on the team can open a browser and test the app on a real simulator, without Xcode, without device setup, without accounts on external services.
Two testing modes
- Manual testing (primary): CI uploads a build → team reviews in the browser. This is tapflow's main use case.
- AI Agent via MCP (experimental): An LLM agent controls the simulator automatically using
@tapflowio/mcp-server. This is a separate, opt-in feature — it does not affect the manual testing path.
When designing features or writing docs, default to the manual testing perspective. The AI Agent path is additive, not a replacement.
WHY
- Appetize / BrowserStack are expensive and send app data outside your network.
- Reuses infrastructure (Mac) the team already owns.
- Fully open-source and customizable.
For the product direction and philosophy behind these — Manual First, Flow Capture as the moat, AI as an additive harness — see VISION.md.
Core Principles
- Evidence-based: verify a root cause with code, logs, or tests before fixing — no guess-driven changes.
- Minimal changes: stay within the requested scope; follow the file's existing conventions. Scope is decided by what a reviewer has to hold in their head, not by which file a line sits in.
- Verifiable goal: know how success will be measured before starting (a reproducing test, same tests passing after a refactor, etc.).
- Stop before risky actions — get user confirmation before any hard-to-reverse operation (
git push --force,git reset --hard, sending messages to external systems, DB drops, etc.). Specifically:- Only create commits or PRs when the user explicitly requests it.
- Do not merge PRs. Always leave merging to the user — even with
--admin. Create the PR and stop. Enforced by the PreToolUse hook.claude/hooks/pr-merge-guard.sh, which blocksgh pr mergeandgh pr reviewin command position. It does not cover thegh apiand git plumbing equivalents: same threat model, a cooperative agent rather than an adversary. - Avoid breaking changes. If unavoidable, report to the user and get approval before proceeding. Breaking change scope: public API / interface signature changes, DB schema changes, WebSocket message protocol changes, CLI command / flag changes.
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 Changed · +17 lines · +335 tokens per session a3ae91c76ac7
- 2d ago First seen · 279 lines · 4,561 tokens per session scan A 7f7f29660e65
tapflow AGENTS.md is an instructions file published in the GitHub repository jo-duchan/tapflow (543 stars, last pushed yesterday), licensed MIT. It adds 4,896 tokens to every session, about $0.0245 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 2026-08-30.
Other instructions, from other repositories
react-native-restart CLAUDE.md
Instructions for avishayil/react-native-restart, covering claude.md, what this is, architecture, repository map and common commands.
metamask-mobile AGENTS.md
AGENTS.md instructions for MetaMask/metamask-mobile, covering agents.md, project overview, essential commands, setup & installation and expo development (recommended for js-only development).
react-native-true-sheet AGENTS.md
Instructions for lodev09/react-native-true-sheet, covering agent instructions, rules, project overview, project structure and view hierarchy.
argent CLAUDE.md
Claude Code instructions for software-mansion/argent, covering argent and documentation.
uniwind AGENTS.md
AGENTS.md instructions for uni-stack/uniwind, covering agent instructions, checks and issue and pr guidelines.
maui-labs devflow-architecture.instructions.md
Instructions for dotnet/maui-labs, covering devflow architecture, communication model, package dependency graph, the abstractions / backend split and key extension points.