Codewhale is an open-source coding agent that runs in the terminal and can read repositories, edit files, execute commands, and inspect results while pursuing a task. Developers use it with hosted providers or local models, with controls for how much access it receives.
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 computer-usegit 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/computer-use)<a href="https://agentmods.dev/skills/hmbown/codewhale/computer-use"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/computer-use/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/skills/hmbown/codewhale/computer-use"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/computer-use.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.06374 |
| Opus 5.5 | $0.00024 | $0.02550 |
| Sonnet 5.5 | $0.00012 | $0.01275 |
| Haiku 4.5 | $0.00006 | $0.00637 |
Grade A, and why
computer-use 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 17d 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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codewhale Computer Use
Computers first
The plugin controls computers, not "the screen". computer {action:"list"} shows the
registry; one computer is always active, and every tool acts on the active
computer unless given computer.
A computer is an execution environment, not necessarily the user's desktop. The registry holds two kinds:
- Spawned computers are ours.
computer {action:"spawn", id:"<id>", transport:"docker"}provisions a disposable Linux desktop container, registers it, and makes it active. Every tool works on it unchanged; the user's own machine is never touched. It is destroyed bycomputer {action:"remove"}or when the session ends. Prefer a spawned computer for any work that does not need the user's own session — it is the isolated workspace, not a workaround for sharing theirs politely. - Registered computers are someone's.
localis the machine the plugin runs on — the user's desktop, with their logged-in apps and their pointer.sshcomputers run the bundled remote agent (pushed automatically at registration).hdccomputers are HarmonyOS devices driven over hdc. Reach forlocalonly when the task genuinely needs that session — their Mail, their signed-in browser, their files on screen. A spawned desktop cannot replace that, and pretending otherwise is the failure mode this distinction exists to prevent.
Other rules:
- Pass
computer: "<id>"on any tool to act on (and stickily switch to) that computer.computer_switchchanges the active computer without acting. - Every receipt names the computer it happened on. Read it before continuing — never assume the action landed on the machine you meant.
- Spawned containers are task-owned: never register one as a normal computer, and never treat its filesystem or state as durable — it dies with the task.
Human controls
When the local helper is installed, it owns the input route even when the
host also includes a native binary. A disconnected helper is an error, never
permission to bypass it with direct input. control_paused and
control_stopped mean the person paused or stopped Computer Use. Stop acting
and wait for them; do not change environment variables, restart the helper,
create another session or use another tool to defeat their choice. After Stop,
the old session remains invalid even when the person allows new sessions.
The helper's own setup, permission and safety controls belong to the person.
Do not operate them or approve the host's pending authorization yourself.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed · +7 lines 410feb9a3690
- 26d ago Changed · +43 lines c05fc7a9ad34
- 29d ago Changed · +107 lines · +15 tokens per session 6e19ed02dbca
- 1mo ago Changed · +79 lines eec00e99412b
- 1mo ago Changed · +31 lines 937e1ec21399
- 1mo ago Changed · +21 lines · +1 tokens per session 8652c8979946
- 1mo ago Changed · +27 lines 51ebf16d5e4f
- 1mo ago Changed · +38 lines 5741d7833e3e
- 1mo ago Changed · +60 lines · +15 tokens per session 9e7d3c85bb3f
- 1mo ago First seen · 39 lines · 28 tokens per session scan A 4c97d0e7250b
computer-use is a skill published in the GitHub repository Hmbown/Codewhale (41,035 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 6,374 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
best-of-n
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers.
handoff
Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / 'pass the baton' / 'hand off', or a long-running operation needs a durable state checkpoint.