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/rejifald/stitchapi/claude-mdgit clone --depth 1 https://github.com/rejifald/StitchAPIWrote 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/rejifald/stitchapi/claude-md)<a href="https://agentmods.dev/instructions/rejifald/stitchapi/claude-md"><img src="https://agentmods.dev/badge/instructions/rejifald/stitchapi/claude-md.svg" alt="Measured on agentmods" 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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
StitchAPI CLAUDE.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 5d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StitchAPI — working agreement for Claude
Edit in a fresh worktree off main
Before writing or editing any file in this repository, call EnterWorktree
first so the session works in a fresh git worktree branched from main. Do not
edit the primary checkout directly.
EnterWorktreeuses thefreshbase ref (configured in .claude/settings.json), so every worktree branches fromorigin/main— the repository's default branch.- Enter the worktree once per session, before the first edit. All edits and the working branch live there.
mainis the default target branch: open the resulting PR againstmain.- Exception: small edits to repo configuration (
.claude/,CLAUDE.md, or memory files) may be made in the primary checkout directly — bootstrapping the worktree rule from inside a worktree isn't worth the friction.
node_modules in a fresh worktree
A fresh worktree has no node_modules (it's gitignored). This is handled
automatically: a hook in .claude/settings.json runs
pnpm install --frozen-lockfile --prefer-offline the moment an EnterWorktree
worktree is created. The global pnpm store (~/Library/pnpm/store) is shared
across all checkouts, so it's fully offline and fast (~5–7s — nothing is
re-downloaded; file content is hardlinked). It creates the per-package
node_modules the pnpm workspace needs and runs lefthook install so the
worktree's git hooks are wired up.
If you ever land in a worktree without deps (e.g. the hook was disabled), run that
same command by hand. Don't symlink node_modules into the worktree — pnpm would
write through the symlink into the primary checkout's store. A real pnpm install
is the correct fix.
Using the StitchAPI docs MCP
This repo ships the stitchapi-docs MCP server preconfigured in
.mcp.json — the local, offline
@stitchapi/docs-mcp
package, which answers from a docs bundle on your machine (no per-query network;
a one-time embedding-model download on first use). For any question about
StitchAPI's own public API, configuration, errors, or runtime behavior, use it
before answering:
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.
- 5d ago First seen · 60 lines · 738 tokens per session scan A e459e5575057
StitchAPI CLAUDE.md is an instructions file published in the GitHub repository rejifald/StitchAPI (18 stars, last pushed today), licensed Apache-2.0. It adds 738 tokens to every session, about $0.0037 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
alpaca-trade-api-js AGENTS.md
AGENTS.md instructions for alpacahq/alpaca-trade-api-js, covering agents.md, conventions, commands, releases & changelog (changesets) and automated release flow on master.
fli CLAUDE.md
Instructions for punitarani/fli, covering claude.md, project overview, development commands, core development tasks and install dependencies.
whoop-mcp CLAUDE.md
Claude Code instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, project structure and code conventions.
huly-mcp CLAUDE.md
Claude Code instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.
frontmcp AGENTS.md
AGENTS.md instructions for agentfront/frontmcp, a project described as: TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
keryx CLAUDE.md
Claude Code instructions for actionhero/keryx, covering claude.md, project overview, monorepo structure, development environment and environment setup.