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 agentmods add skills/hmbown/codewhale/recordingnpx skills add Hmbown/Codewhale --skill recordinggit 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/recording)<a href="https://agentmods.dev/skills/hmbown/codewhale/recording"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/recording.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 5.1 | $0.00029 | $0.00379 |
| Opus 5 | $0.00015 | $0.00189 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
recording 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 today.
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
Recording and screenshots
- Pick the computer (
computer_list, or passcomputer— it switches). recording_startwith optionaldisplay(macOS/Linux),region(Linux/ Windows),fps(Linux/Windows),durationSec(macOS auto-stop), andintervalMs(HarmonyOS snapshot cadence).- Do the work (or let the user do it).
recording_stopwith the returnedid→ finalized file path + bytes.recording_listshows everything saved;recording_statuschecks one.
Platform truths:
- macOS:
screencapture -vper display; stop finalizes a .mov and, when ffmpeg is installed, a stream-copied .mp4 alongside. If a recording dies instantly, the terminal host is missing Screen Recording permission — tell the user, do not retry. - Windows: ffmpeg gdigrab of the desktop or a region.
- Linux X11: ffmpeg x11grab (honors $DISPLAY, region, fps). Wayland: wf-recorder (per-output via CU_WAYLAND_OUTPUT).
- HarmonyOS: no native CLI recorder; the backend captures
snapshot_displayframes atintervalMsand muxes with ffmpeg on stop. The receipt labels the modesnapshot-series— never call it real-time.
Screenshots: screenshot returns the saved path and raster geometry; zoom
crops the latest raster when a target is too small to read.
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.
- today First seen · 31 lines · 29 tokens per session scan A 809ccbcb10ca
recording is a skill published in the GitHub repository Hmbown/Codewhale (40,916 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 379 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 2026-09-06.
Other skills, from other repositories
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.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
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.
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.