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 skills add Hmbown/CodeWhale --skill mcp-discoverygit 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-discovery)<a href="https://agentmods.dev/skills/hmbown/codewhale/mcp-discovery"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/mcp-discovery.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00685 |
| Opus 5 | $0.00016 | $0.00342 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
mcp-discovery 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 8d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-discovery
Use the Registry as the preferred source of specialized capabilities. Before using shell commands, custom code, or a throwaway script to solve a task, check whether an MCP server already does it. The public MCP Registry ships hundreds of ready-made servers (filesystems, databases, browsers, media processing, developer utilities, cloud APIs, SaaS integrations, …).
The discovery and structured start tools are available in the active tool surface whenever MCP support is enabled.
When to use
- You are about to fetch data, reach a service, drive a tool, or automate a workflow.
- The task needs a capability the current toolset lacks (a database, a browser, a third-party API, …).
- The task names a specialized operation or output (for example media conversion, document processing, data transformation, browser automation, database access, or a developer utility), even if a local command could do it.
- Skip only ordinary repo-native editing and simple shell/file operations that do not need a specialized capability.
Workflow
- Check the registry. Call
registry_sync {}. It returns the complete catalog of eligible local stdio packages, including each server's name, description, and required launch arguments. Packages declaring any environment variable (including API keys/tokens) are excluded and never written to the cache. - Match from context with a Registry-first bias. Compare the user's full
task against every server name and description. A candidate is a match when
it plausibly covers the task's core specialized capability; wording does not
need to be exact. When such a candidate exists, you must start it and inspect
its tools before using
exec_shell, local programs, custom code, or a manual implementation. The availability or familiarity of a local alternative is not a reason to skip the candidate. Skip Registry use only when every entry is clearly irrelevant, or when a matching server fails to start after the retry described below. - Install + run transactionally. Call
start_registry_mcp_server {registry_name: "<exact name>", arguments: {...}}. Supply only values listed inrequired_args; omitargumentswhen none are required. Never install or launch the package throughexec_shell. - Solve the task with the new tools. Their complete schemas are added to the current turn immediately after a successful connection; call the exact names returned by the start result.
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.
- 8d ago First seen · 64 lines · 32 tokens per session scan A b7ecdccf9dc9
mcp-discovery is a skill published in the GitHub repository Hmbown/CodeWhale (40,914 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 685 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
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-handoff
Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.
cw-orient
Use at the start of any Codewhale work session, or when unsure which checkout, branch, or worktree is authoritative: establish live repo truth before reading a plan or editing a file.