Borrowing it
Nothing to install: this file belongs to semwalajay83-sem/salesforce-metadata-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/semwalajay83-sem/salesforce-metadata-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/semwalajay83-sem/salesforce-metadata-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/semwalajay83-sem/salesforce-metadata-mcp/claude-md)<a href="https://agentmods.dev/instructions/semwalajay83-sem/salesforce-metadata-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/semwalajay83-sem/salesforce-metadata-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/semwalajay83-sem/salesforce-metadata-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/semwalajay83-sem/salesforce-metadata-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 | $0.03145 | $0.03145 |
| Opus 5 | $0.01572 | $0.01572 |
| Sonnet 5 | $0.00629 | $0.00629 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
salesforce-metadata-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 9d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
salesforce-metadata-mcp — Project Context
What this is
An open-source npm MCP server (package: salesforce-metadata-mcp, npm user: semwalajay)
that lets Claude create and manage Salesforce metadata via natural language.
Public GitHub repo: https://github.com/semwalajay83-sem/salesforce-metadata-mcp
Tool count: 228 (verify by counting unique "sf_..." registerTool names across src/tools/*.ts before quoting in docs).
CRITICAL RULES
Git is the source of truth
- After EVERY bug fix or feature addition, commit and push to git IMMEDIATELY
- Do not wait until the end of a session, commit after each individual fix
- The VM is disposable. Git is not. Everything must be recoverable from git alone.
npm publish rules
- NEVER run npm publish unless the user explicitly says "publish to npm"
- When publishing: always pull from git into a clean directory first, build there, then publish
- Never publish from the VM working directory directly
Org rules
- ONLY use the designated personal dev org — never any employer or customer org
- Default test org alias: secondorg
- Org URL, username, and IDs live in CLAUDE.local.md (gitignored)
Dev Environment
- Current machine: Windows 11 desktop (C:\Users\Ajay\salesforce-metadata-mcp)
- Previous machine: Google Cloud VM (user: semwalajay83) — no longer used
- npm automation token stored in ~/.npmrc
- Claude Code: always run with --dangerously-skip-permissions
Auth — JWT Bearer Flow (no browser, auto-refreshes)
- All credentials (SF_INSTANCE_URL, SF_JWT_CLIENT_ID, SF_JWT_KEY_FILE, SF_JWT_USERNAME)
live in
.env.local(gitignored); see CLAUDE.local.md for details - Test runners (run-tests.mjs, run-tests-complex.mjs) load
.env.localautomatically
Git Workflow
After every fix: git add -A git commit -m "fix: describe what was fixed" git push origin main
Before publishing (only when user asks): cd /tmp && git clone sf-mcp-publish cd sf-mcp-publish && npm install && npm run build npm publish --access public
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.
- 9d ago First seen · 169 lines · 3,145 tokens per session scan A c2468af759bd
salesforce-metadata-mcp CLAUDE.md is an instructions file published in the GitHub repository semwalajay83-sem/salesforce-metadata-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 3,145 tokens to every session, about $0.0157 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.