Borrowing it
Nothing to install: this file belongs to tabbykat113/ksp-mods-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/tabbykat113/ksp-mods-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/tabbykat113/ksp-mods-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/tabbykat113/ksp-mods-mcp/claude-md)<a href="https://agentmods.dev/instructions/tabbykat113/ksp-mods-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tabbykat113/ksp-mods-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/tabbykat113/ksp-mods-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tabbykat113/ksp-mods-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 | $0.01851 | $0.01851 |
| Opus 5 | $0.00925 | $0.00925 |
| Sonnet 5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
ksp-mods-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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ksp-mods-mcp — notes for Claude
Project overview
A uv Python project with two components:
harvestCLI — downloads and indexes KSP mod metadata from CKAN-meta into a local SQLite DBksp-mods-mcp— stdio MCP server that exposes search/lookup tools over that DB
Architecture
harvester/
db.py — SQLite schema, all query/write functions, KSP version logic
harvest.py — tar.gz streaming, parsing loop, CLI entry point
enrichment.py — lazy GitHub/SpaceDock fetchers, cache read/write, TTL logic
ckan_cache.py — CKAN download cache detection (URL hashing, ZIP scanning)
parts.py — KSP part extraction from cached ZIPs (CFG parser, localization)
mcp_server/
server.py — FastMCP tool definitions, error handling wrapper
explore_mod.py — standalone exploration script (not part of the package)
Key design decisions
- Single tar.gz download for Pass 1 — one request gets all ~4000 mods, same approach as CKAN's own C# client. URL:
https://github.com/KSP-CKAN/CKAN-meta/archive/refs/heads/master.tar.gz - ETag-based skip — re-running harvest is a no-op if nothing changed upstream. ETag stored in the
metatable. - Schema versioning —
SCHEMA_VERSIONconstant indb.py.run_harvest()auto-forces a re-harvest when the stored version inmetais stale. BumpSCHEMA_VERSIONwhenever a schema change requires re-harvest; no manual--forceneeded. mod_versionstable — stores every.ckanfile as a version row (~29k rows). Themodstable stores one row per unique identifier, populated from the latest-by-release_dateversion entry (accumulated in Python during the tar pass, bulk-inserted after). Version history is used for KSP compatibility filtering.max_ksp_version— denormalized ontomodsat harvest time. Normalized tomajor.minor, capped at1.12(KSP1 ceiling). Mods with no upper bound or no constraints default to1.12.- KSP version filter — prefix-based tuple comparison in Python (
identifiers_supporting_ksp), not SQL. Runs against the fullmod_versionstable then passes a set of identifiers into the WHERE clause. - Platform-aware DB path — defaults to
~/.local/share/ksp-mods-mcp/ckan.db(Linux) orAppData/Local/ksp-mods-mcp/ckan.db(Windows).CKAN_DBenv var overrides. - Lazy harvest on first tool call — the server triggers
run_harvest()on the first tool invocation (not at startup), keeping MCP startup instant. ETag check makes subsequent calls a no-op. - Error handling in tools —
@_tooldecorator catches all exceptions and returns them as{"error": "..."}JSON so the model gets a readable message rather than a traceback. - CKAN download cache detection —
ckan_cache.pyscans the CKAN downloads directory once per session, builds a set of 8-char URL hashes from ZIP filenames, and answersis_cached(url)in O(1). CKAN hashes the percent-decoded URL (not the raw encoded form).download_urlinmodsstores all mirror URLs newline-separated so any mirror match counts. Only the latest version's URLs are checked — an older cached ZIP does not setis_cached. - Part extraction —
parts.pyopens a cached ZIP, scansGameData/{identifier}/Parts/**/*.cfg, parses KSP's CFG format (brace-depth tracking for MODULE/RESOURCE sub-blocks), and resolves#LOC_...strings fromGameData/{identifier}/Localization/en-us.cfg. Bundled deps under otherGameData/subdirectories are ignored.
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.
- 8d ago First seen · 101 lines · 1,851 tokens per session scan A f3622981dacf
ksp-mods-mcp CLAUDE.md is an instructions file published in the GitHub repository tabbykat113/ksp-mods-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,851 tokens to every session, about $0.0093 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
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.