Borrowing it
Nothing to install: this file belongs to jabbawocky/statuscraft. 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/jabbawocky/statuscraft/main/CLAUDE.mdgit clone --depth 1 https://github.com/jabbawocky/statuscraftWrote 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/jabbawocky/statuscraft/claude-md)<a href="https://agentmods.dev/instructions/jabbawocky/statuscraft/claude-md"><img src="https://agentmods.dev/badge/instructions/jabbawocky/statuscraft/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 5.1 | $0.00963 | $0.00963 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
statuscraft 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 6d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StatusCraft — CLAUDE.md
MCP server (stdio) that checks the live status of ~3,600 software services from their official status pages. Published straight from GitHub — users install with npx -y github:jabbawocky/statuscraft (no API key, no npm registry).
GitHub account
This repo belongs to the jabbawocky GitHub account, NOT leadsyapplication. Run gh auth switch -u jabbawocky before any push/PR/gh command here, and switch back after if other work follows.
Architecture — one file
Everything lives in src/index.ts (~8,000 lines):
SERVICESarray (starts ~line 77): 3,629ServiceConfigentries —{ id, name, tags, status_url, page_url, type }.- Fetchers (after the array): one per
type—statuspage(the default, Atlassian Statuspage/api/v2/status.json), plus custom handlersgcp,slack,azure,aws,incidentio,pagerduty,heroku,statusio,betterstack,salesforce(Trust API, aggregates production instances). - 5 MCP tools:
get_status,get_all_status,list_services,check_multiple,refresh_status. - 60-second in-memory cache (
CACHE_TTL_MS); outbound fetches batched atFETCH_CONCURRENCY = 50to avoid fd exhaustion at this scale. - Incident detail is only fetched for non-operational services (no latency cost when green).
Build & ship — dist/ is committed on purpose
npm run build (plain tsc) emits dist/index.js. Because installs come directly from GitHub via npx github:... with no publish step, dist/ is checked into git — always rebuild and commit dist/ alongside any src/ change, or users get stale code.
Working conventions (from STATUS.md history)
STATUS.mdis a rolling mission log in "ticks" — newest entry at the top. Each expansion tick records: services added, count change (e.g. 4056 → 4066), verification results, and a health spot-check of core fetchers (Anthropic, GitHub, Datadog, Sentry, etc.). Append a new entry per work session.- Every new service is live-verified before commit — actually hit its
status_urland confirm a valid response. No unverified entries. - The service count appears in several places that must stay in sync: README header/intro, the tool descriptions inside
src/index.ts, and the STATUS.md tick.grep -c 'id: "' src/index.tsis the source of truth (3,355 as of 2026-07-18, after removing 436 duplicate-ID entries and 274 alias-dupe entries that expansion ticks had accumulated). Before adding a service, grep for its id AND its status_url — duplicate IDs are bugs (get_statusonly reaches the first match), and this repo has been burned by re-adding existing services.node audit-dupes.mjsmust report 0 duplicate URLs. - When a service rebrands, keep ONE entry and put the former brand in the display name (e.g. "Splunk On Call (VictorOps)") —
get_statusfalls back id → exact name → name-substring, so that keeps old-brand queries resolving without a second entry. - Adding a Statuspage-backed service is a 6-line entry in the
SERVICESarray; non-standard pages need one of the existing customtypehandlers.
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.
- 6d ago First seen · 42 lines · 963 tokens per session scan A 80b91076c3c5
statuscraft CLAUDE.md is an instructions file published in the GitHub repository jabbawocky/statuscraft (1 stars, last pushed 1mo ago), licensed MIT. It adds 963 tokens to every session, about $0.0048 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
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).
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.
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).
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.