Borrowing it
Nothing to install: this file belongs to dapperAuteur/flashlearn-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/dapperAuteur/flashlearn-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/dapperAuteur/flashlearn-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/dapperauteur/flashlearn-mcp/claude-md)<a href="https://agentmods.dev/instructions/dapperauteur/flashlearn-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dapperauteur/flashlearn-mcp/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 | $0.01216 | $0.01216 |
| Opus 5 | $0.00608 | $0.00608 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
flashlearn-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 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flashlearn-mcp
A standalone TypeScript MCP (Model Context Protocol) server that wraps the FlashLearnAI
public API (/api/v1) so any MCP client (Claude Code, Claude Desktop, others) can browse
decks, generate flashcards, and run SM-2 study sessions. stdio transport in v1.
Ecosystem repo identity (don't confuse these)
This repo (claude/flashlearn-mcp) is the MCP wrapper only. It is NOT the FlashLearnAI
product (claude/flashlearn-ai, which owns the API, the database, and the web app) and NOT
the parent WitUS site (gemini/witus). Do not build API endpoints here: if the wrapper
reveals an API gap, file it in flashlearn-ai/plans/ instead. The FlashLearnAI OpenAPI
spec (flashlearn-ai/lib/api/openapi.ts, served at /api/v1/openapi) is the contract this
repo codes against; where spec and route code disagree, note it upstream, never encode the
discrepancy silently here.
The site brandanthonymcdonald.com (BAM's personal portfolio) lives in
claude/bam-landing-page/, NOT projects/bam-portfolio/ (the retired legacy static
site). When asked to work on the portfolio, target bam-landing-page.
Full ecosystem identity plus the canonical product index live in gemini/witus/CLAUDE.md.
Don't infer another app's URLs, routes, IDs, env names, or DB schema: confirm against that
app's own code.
Operator-task rule (pointer)
Any work that needs BAM to act outside the editor (API key minting, GitHub repo creation,
npm publish, env vars, vendor dashboards) gets a file in ./plans/user-tasks/NN-slug.md
with scope tag, what + why (explicit blocking detail), steps, what Claude will use, how to
mark done, and related links. No exceptions for small steps. This repo also keeps a
TASKS-FOR-BAM.md at the root per the build brief. Ecosystem-wide tasks live in the
canonical queue at gemini/witus/plans/user-tasks/. Full rule: gemini/witus/CLAUDE.md
section "Operator-task rule".
Branch-hygiene rule (pointer)
Half 1: Claude branches, commits, pushes, and never touches main (branch -> commit ->
push -> stop; re-check git branch --show-current before every commit). Half 2: BAM merges
pushed branches between sessions by default, so assume prior branches are merged at session
start and beware the silent fast-forward trap mid-session. Half 3: keep branches small (one
concern each) and bundle multiple branches into one bundle/<slug>-YYYY-MM-DD with
git merge --no-ff before handoff so BAM does one merge. Commit often, at every working
checkpoint. A checked-in .githooks/pre-commit refuses commits on main/master;
activate once per clone with git config core.hooksPath .githooks. Full text:
gemini/witus/CLAUDE.md section "Branch-hygiene rule".
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 · 89 lines · 1,216 tokens per session scan A c9cdb343fc7f
flashlearn-mcp CLAUDE.md is an instructions file published in the GitHub repository dapperAuteur/flashlearn-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,216 tokens to every session, about $0.0061 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).
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).
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.
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.