Hmbown/CodeWhale is an open-source coding agent that runs in the terminal and is written in Rust. Developers use it to inspect repositories, edit files, run commands, and coordinate work with configurable model providers, skills, MCP servers, and approval controls; the catalogue entries extend its available workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hmbown/codewhale/mcp-buildernpx skills add Hmbown/CodeWhale --skill mcp-buildergit clone --depth 1 https://github.com/Hmbown/CodeWhaleWrote 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/skills/hmbown/codewhale/mcp-builder)<a href="https://agentmods.dev/skills/hmbown/codewhale/mcp-builder"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/mcp-builder.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 | $0.00030 | $0.00366 |
| Opus 5 | $0.00015 | $0.00183 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
mcp-builder 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 5d 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
MCP Builder
Use this skill when the user asks to create, configure, or debug an MCP server or tool integration.
Design Rules
- Prefer stdio MCP servers for local tools and HTTP/SSE for remote services.
- Keep tool schemas small, typed, and explicit. Return structured JSON where possible.
- Put secrets in environment variables, never in committed config.
- For HTTP/SSE clients, send
Accept: application/json, text/event-streamby default unless the server explicitly requires something else. - Add timeouts and clear error messages around external APIs.
Codewhale Setup
Common commands:
codewhale mcp init
codewhale mcp add my-server --command node --arg server.js
codewhale mcp add remote-server --url http://127.0.0.1:3000/mcp
codewhale mcp list
codewhale mcp validate
codewhale mcp tools
HTTP/SSE entries can include per-server headers in ~/.codewhale/mcp.json when
credentials or custom routing headers are required.
Workflow
- Define the service boundary and the minimum useful tools.
- Choose transport and credential handling.
- Implement the server using a maintained MCP SDK when available.
- Add the server with
codewhale mcp addor edit~/.codewhale/mcp.json. - Run
codewhale mcp validate, thencodewhale mcp tools. - Test one happy path and one failure path before calling it done.
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.
- 5d ago First seen · 45 lines · 30 tokens per session scan A 49cff44bc429
mcp-builder is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 366 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
computer-use
See the screen and operate it. Use when the user asks to click, type, or check something visually on this machine.
ship-and-babysit
End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.
claw-orchestrator
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel…
write-documentation
Write and format Rust documentation correctly. Apply proactively when writing code with rustdoc comments (//! or ///). Covers voice & tone, prose style (opening lines, explicit subjects, verb tense), structure (inverted pyramid), intra-doc links (crate:: paths, reference-style), constant conventions (binary/byte…
organize-modules
Apply private modules with public re-exports (barrel export) pattern for clean API design. Includes conditional visibility for docs and tests. Use when creating modules, organizing mod.rs files, or before creating commits.
ultraapp-interview
Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.