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 commands/openclaw/peekaboo/learngit clone --depth 1 https://github.com/openclaw/PeekabooWhat 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 | $0.00000 | $0.00532 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
learn 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peekaboo learn
peekaboo learn prints the canonical background-only public Agent guide. It stitches together the matching generated system prompt and Shell-free Agent tool registry, best-practice checklists, common workflows, and the full Commander signature table so other runtimes can stay in sync with the CLI release.
What it emits
- System instructions straight from background-only
AgentSystemPrompt.generate(), including communication rules and safety guidance. - Tool catalog grouped by category with each public Agent tool’s abstract, required/optional parameters, and JSON examples (if available). Shell is not a public Agent tool.
- Best practices + quick reference: long-form guidance for automation patterns, then a condensed cheat sheet.
- Commander section: a programmatic dump of every CLI command’s positional arguments, options, and flags (built by
CommanderRegistryBuilder.buildCommandSummaries()).
Implementation notes
- The command is intentionally text-only—
--jsonis ignored—so downstream systems should capture stdout if they want to cache the content. - Everything runs on the main actor because it pulls the same background-only, policy-filtered toolset as a normal Agent session plus live Commander metadata; no parallel discovery catalog is involved.
- Because it reuses the same builders the CLI uses at runtime, new commands/tools automatically show up here as soon as they land.
- Background-only typing examples use a fresh exact non-dialog snapshot; app/PID/window-selector-only Agent typing is intentionally absent because policy refuses it.
- When stdout is a rich TTY, output is rendered with Swiftdansi for ANSI color and table/box formatting; piped output stays plain Markdown for downstream tools.
Examples
# Save the full guide for another agent runtime
peekaboo learn > /tmp/peekaboo-guide.md
# Extract just the Commander signatures
peekaboo learn | awk '/^## Commander/,0'
Troubleshooting
- Verify Screen Recording + Accessibility permissions (
peekaboo permissions status). - Confirm your process with
peekaboo app list, its exact window withpeekaboo window list, and current UI withpeekaboo seebefore rerunning. - Re-run with
--jsonor--verboseto surface detailed errors.
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 · 38 lines · 0 tokens per session scan A 5684b5e16914
learn is a command published in the GitHub repository openclaw/Peekaboo (5,098 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 532 tokens. 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 commands, from other repositories
upload
Archive, upload, and submit to external TestFlight (full loop with monitor).
release
Create a new Remarc release using the automated GitHub Actions workflow.
imark-review
Open a markdown document in Imark for review and wait for the reviewer's notes.
imark-notes
Read the Imark comments out of a markdown file.
archive
Create xcarchive for TestFlight.
build
Build debug and launch HomeClaw.