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/plugin-creatornpx skills add Hmbown/CodeWhale --skill plugin-creatorgit clone --depth 1 https://github.com/Hmbown/CodeWhaleWhat 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 | $0.00029 | $0.00585 |
| Opus 5 | $0.00015 | $0.00293 |
| Sonnet 5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
plugin-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Creator
Use this skill when a user wants a local Codewhale plugin bundle. Codewhale v0.9.1 has a deliberately bounded loader: trusted and enabled bundles may add declarative Skills and MCP servers through the existing engines. Other component kinds are inventory-only.
Workflow
- Pick a Codewhale-owned location:
- User bundle:
~/.codewhale/plugins/<plugin-name>/ - Workspace bundle:
<workspace>/.codewhale/plugins/<plugin-name>/
- User bundle:
- Normalize the bundle name to lowercase hyphen-case.
- Create
plugin.toml:
schema_version = 1
[plugin]
name = "my-plugin"
version = "0.1.0"
description = "What this bundle provides"
[skills]
path = "skills"
- Put each Skill under
skills/<skill-name>/SKILL.md. Codewhale exposes it asmy-plugin:<skill-name>, never as an unqualified command. - Add
[mcp_servers.<name>]only when the bundle needs an existing MCP engine. Keep stdio commands and paths inside the bundle. Map local environment values only as exact${SOURCE_ENV}references. For remote MCP, use HTTPS (or loopback HTTP), forbid URL user information/query/fragment, use only environment-backed headers or bearer tokens, and declare the exact normalized endpoint host set in[capabilities].network_hosts. Never place credentials in the manifest. - Declare commands, agents, hooks, LSP, native extensions, filesystem roots, or lifecycle mutation only when inventorying future work. Codewhale shows them as inactive and still activates reviewed Skills and MCP from the same bundle. A bundle that only declares those unsupported surfaces cannot be enabled.
- Validate and review without executing bundle content:
/plugin validate <plugin-name>/plugin show <plugin-name>/plugin enable <plugin-name>to open the content/capability review- run the exact
/plugin trust ...confirmation shown, then enable again
- Verify
/skills inspectreports plugin provenance and/plugin listreports the expected trust and activation state. Trust stages the reviewed content but does not activate it; enablement rebuilds the current workspace's Skill/MCP catalogue immediately.
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.
- 2d ago First seen · 60 lines · 29 tokens per session scan A 09521548e0d7
plugin-creator is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 585 once invoked, about $0.0001 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
Session Monitoring
Provides awareness of claudectl session state, health checks, and cost tracking. Activated when the user asks about session health, spending, brain decisions, or multi-session coordination.
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
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.
check-bounds-safety
Apply type-safe bounds checking patterns using VPIndex/VPLength types instead of usize. Use when working with arrays, buffers, cursors, viewports, or any code that handles indices and lengths.
check-code-quality
Run comprehensive Rust code quality checks including compilation, linting, documentation, and tests. Use after completing code changes and before creating commits.
analyze-performance
Establish performance baselines and detect regressions using flamegraph analysis. Use when optimizing performance-critical code, investigating performance issues, or before creating commits with performance-sensitive changes.