Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/christopherlouet/claude-basenpx agentmods add commands/christopherlouet/claude-base/dev-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/commands/christopherlouet/claude-base/dev-mcp)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/dev-mcp"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-mcp/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/commands/christopherlouet/claude-base/dev-mcp"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-mcp.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 | $0.00000 | $0.00396 |
| Opus 5.5 | $0.00000 | $0.00158 |
| Sonnet 5.5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
dev-mcp 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 1mo 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.
What it actually says
Agent DEV-MCP (pointer)
Guide for creating quality MCP (Model Context Protocol) servers.
Context
$ARGUMENTS
Delegate to the vendor toolkit
claude-base's prior dev-mcp content is superseded by anthropics/skills › mcp-builder — the protocol authors' own skill. It covers MCP server design (workflows-not-endpoints, tool annotations, input validation, actionable errors, evaluation) for both Python (FastMCP) and the Node/TS SDK, at a depth and currency a hand-maintained checklist cannot match; this command wrapped a protocol the vendor owns.
Install:
# Vendor path (verify on their README):
npx skills add anthropics/skills
# Fallback — clone the canonical repo:
git clone --depth 1 https://github.com/anthropics/skills ~/dev/vendor-skills/anthropic
ln -s ~/dev/vendor-skills/anthropic/skills/mcp-builder ./.claude/skills/mcp-builder
Recipe entry: docs/recipes/recommended-vendor-skills.md §"Anthropic — mcp-builder". Reduction rationale: specs/graduation-supply-audit/spec.md.
Related agents
| Agent | Usage |
|---|---|
/dev:dev-api |
If creating a REST API in parallel |
/dev:dev-tdd |
MCP server tests |
/doc:doc-api-spec |
OpenAPI documentation of the target API |
YOU MUST validate all inputs (Pydantic/Zod) and return actionable errors; NEVER expose internal technical details in error messages.
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.
- 1mo ago First seen · 36 lines · 0 tokens per session scan A 113aa64ed592
dev-mcp is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 396 tokens. 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 2026-09-03.
Other commands, from other repositories
migrate
Generate and manage database migrations.
scaffold
Scaffold project components from templates.
deploy
Deploy application with pre/post-deploy checks.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
log-decision
Append an architectural decision to the persistent decision log.
session-log
Explain where session history lives now that the toolkit keeps no session log.