What is elc-toolkit CLAUDE.md?

Project instructions for elc-toolkit, a remote MCP server that provides tools based on Engineering Leaders Collective member data.

Developing, testing, deploying, and maintaining tools for leadership benchmarking, partnership cases, and community-launch readiness.

They explain the server's purpose, data sources, routes, development commands, and deployment process in one place.

How marian-kamenistak/elc-toolkit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to marian-kamenistak/elc-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/marian-kamenistak/elc-toolkit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/marian-kamenistak/elc-toolkit

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/marian-kamenistak/elc-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/marian-kamenistak/elc-toolkit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/marian-kamenistak/elc-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/marian-kamenistak/elc-toolkit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/marian-kamenistak/elc-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/marian-kamenistak/elc-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 872 This file is loaded in full into every session.

When invoked 872 The same file — it is already loaded in full.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00872	$0.00872
Opus 5.5	$0.00349	$0.00349
Sonnet 5.5	$0.00174	$0.00174
Haiku 4.5	$0.00087	$0.00087

Measured 13d ago against content hash 00790beefa4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

elc-toolkit CLAUDE.md scanned grade B with 2 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 13d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- [ ] `curl -s -X POST https://www.engineeringleaders.io/mcp -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` returns **6** — the 6

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] `curl -s -X POST https://www.engineeringleaders.io/mcp -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'` returns **6** — the 6

CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

elc-toolkit

What this is

Remote, authless MCP server for the elc stream, live at https://www.engineeringleaders.io/mcp (docs page at the same URL in a browser; human page at /toolkit/). Six tools: get_started (routes a greeting/test/unclear message to the right tool below), get_more_tools (a real registration, 2026-09-04 — overrides @posthog/mcp's auto-injected virtual tool of the same name so a bare "hi"/"test"/"hello" ping gets the get_started menu instead of a canned "we noted your feedback" dead end; a real capability report still falls through unchanged) plus three backed by ELC's own member data — benchmark_leadership_ratio, build_partnership_business_case, assess_community_launch_readiness. Listed in registries (server.json, mcp.json). Sixth tool since 2026-10-14: plan_leadership_career_path (src/career-path.ts), career path + 6-month plan built from meetup #43; human page /toolkit/career-path/, skill /.well-known/agent-skills/engineering-leader-career-path/SKILL.md in elc-web.

Stack

Cloudflare Worker + Durable Object ElcToolkit (MCP_OBJECT), McpAgent from agents ^0.17, streamable HTTP
TypeScript 6, zod 4, @posthog/mcp + posthog-node for usage analytics
wrangler ^4.105, npm
Routes: engineeringleaders.io/mcp* + www. — owns the /mcp* prefix; elc-partnership-builder nests under /mcp/partnership*

Run / build / deploy / test

# dev:    npm run dev
# build:  npm run type-check
# test:   npm test (vitest; CI runs it before deploy); /ai-mcp-test for persona runs
# deploy: set -a && source ~/.env && set +a && npm run deploy

Sources of truth

Data	Lives in	Id / path
Peer baseline numbers	ELC Data Points (Notion) via Attio `elc_members`	fetch: `node ~/ai/_brand/data-points/dp.mjs`
New-city playbook	`business/elc/playbooks/meetup-new-city.md`
Registry metadata	`server.json`, `mcp.json`, `LAUNCH-STATUS.md`
Secrets	Worker-only, no `.op-secrets`: `MCP_USAGE_SLACK_CHANNEL`, `SLACK_BOT_TOKEN_ELC` (`wrangler secret list`, 2026-08-30)	PostHog key is not a secret — public `posthogKey: "phc_…"` literal in `src/index.ts`

Read the full file on GitHub · 46 lines

Changes

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.

13d ago Changed · +81 tokens per session 00790beefa4b
1mo ago Changed · +5 lines · +117 tokens per session a1036a286e9c
1mo ago First seen · 41 lines · 674 tokens per session scan B 3c099d033b27

Subscribe to this mod's changes

elc-toolkit CLAUDE.md is an instructions file published in the GitHub repository marian-kamenistak/elc-toolkit (0 stars, last pushed 7d ago), licensed MIT. It adds 872 tokens to every session, about $0.0035 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

cloudflare-workers community engineering-leadership engineering-management mcp mcp-server

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).

microsoft/vscode · 9,715 tokens

elc-toolkit: Instructions file for Claude Code