Borrowing it
Nothing to install: this file belongs to chrischall/myhotlunchbox-mcp. 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/chrischall/myhotlunchbox-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/myhotlunchbox-mcpWrote 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/chrischall/myhotlunchbox-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/myhotlunchbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/myhotlunchbox-mcp/claude-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/chrischall/myhotlunchbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/myhotlunchbox-mcp/claude-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 | $0.01470 | $0.01470 |
| Opus 5 | $0.00735 | $0.00735 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
myhotlunchbox-mcp 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 12d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
myhotlunchbox-mcp
Repo-specific notes. Fleet-wide conventions live in ~/.claude/CLAUDE.md and
are deliberately not restated here.
Archetype
Server-side OAuth2 password grant — not a browser bridge, not a captured
cookie. ordernow.myhotlunchbox.com has no bot wall and no CAPTCHA, so
MYHOTLUNCHBOX_USERNAME + MYHOTLUNCHBOX_PASSWORD are the whole configuration.
Do not add a @fetchproxy/server dependency; nothing here needs one.
offline_access in the scope is load-bearing — it is what yields the refresh
token. Drop it and every session needs the password again.
Never retry a rejected credential
/api/auth/login is OpenIddict. A failed attempt is counted, and repeated
failures can escalate to a CAPTCHA that removes server-side sign-in for the
account permanently. MhlbAuth.postGrant throws on the first rejection by
design — do not add a retry loop around it.
The password has no shape
redactSecrets / truncateErrorMessage match secret shapes (Bearer, JWT,
sk-). A password matches none of them. Every error path that renders an
upstream body goes through scrubCredentials(text, [password]), which splices
the literal value out. tests/auth.test.ts and tests/client.test.ts assert the
outcome (the password is absent from the message), not that the wrapper was
called — the wrapper alone would have passed while still leaking.
Ordering is read-modify-write
GET /event/createOrder returns a model; POST /event/createOrder takes it
back. Same for editOrder, createChild, editChild. The site's own compiled
client passes these through opaquely and never names the fields, so the tools do
the same rather than inventing a schema. These are whole-record replaces.
Field names the extraction got wrong
Four things the compiled-client extraction could not tell us, all found by running against a real account. Do not "simplify" any of them back:
/calendar/studentSchoolDatatakesstart/end, notstartDate/endDate. Wrong names return 200 with an emptyeventsarray — a silent wrong answer.tests/tools.test.tspins this./parentReports/print*return binary PDF, not JSON — henceMhlbClient.writeBinary. Their payloads are not date ranges:printCalendarneedsmiddle(the midpoint date),printOrderstakes a singleeventDateplus a non-emptystudentIds, andprintTransactionstakes a whole transaction record.printOrdersanswers 500, not 4xx, for an emptystudentIdsor a date with no matching order.writeBinarywords its 500 hint accordingly — do not replace it with a genericUnreachableError.- Order status enum:
Pending: 0, Paid: 1, Credited: 2.
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.
- 12d ago First seen · 127 lines · 1,470 tokens per session scan A 5996ab9263c6
myhotlunchbox-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/myhotlunchbox-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,470 tokens to every session, about $0.0073 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
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.
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.
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.
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).
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).