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/configgit 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 | $0.01590 |
| Opus 5 | $0.00000 | $0.00795 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade D, and why
config scanned grade D with 2 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 yesterday.
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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
# Add and validate an OpenRouter key with the no-echo prompt Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
printenv OPENAI_API_KEY | peekaboo config credential set openai --credential-stdin --no-input How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peekaboo config
peekaboo config owns everything under ~/.peekaboo/: the JSONC config file, the credential store, and the list of custom AI providers. Each subcommand runs on the main actor so it can call the same ConfigurationManager used by the CLI at startup, which means the output always reflects what the runtime will actually load.
Subcommands
| Subcommand | Purpose | Key flags |
|---|---|---|
init |
Create a default config.json (respects --force) and print provider readiness (env / credentials / OAuth) in human mode. |
--force overwrites an existing file; --timeout bounds live checks (default 30s; bare values are milliseconds). |
show |
Print either the raw file or the fully merged “effective” view (config + env + credentials); human --effective also live-validates providers. |
--effective switches to the merged view; --timeout bounds validation with the shared duration grammar; JSON mode emits a standard { success, data } object with no appended text. |
edit |
Opens the config in $EDITOR (or the --editor you pass) and validates the result after you quit. |
--editor overrides the detected editor. |
validate |
Parses the config without writing anything and surfaces syntax/errors. | None. |
status |
Display provider credential readiness. | --timeout (default 30s; bare values are milliseconds). |
login |
Run an OAuth flow (no API key stored) for supported providers. | login openai (ChatGPT/Codex), login anthropic (Claude Pro/Max). |
credential set |
Validate and store a known provider credential, or store a raw credential key. | With no source, prompts without echo. Scripts use --credential-stdin --no-input or an owner-only --credential-file; --timeout bounds validation. |
provider add |
Append or replace a custom AI provider entry. | Positional <provider-id> plus `--type openai |
provider list |
Dump configured custom providers plus whether they’re enabled. | --json follows the same schema that the runtime loads. |
provider test |
Test the configured endpoint and credentials. | Positional <provider-id>. |
provider remove |
Delete a custom provider entry. | Positional <provider-id> plus optional --force and --dry-run. |
provider models |
List configured models offline, or query an OpenAI-compatible provider with --discover. |
Positional <provider-id> plus optional --discover and --save. |
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.
- yesterday First seen · 77 lines · 0 tokens per session scan D 25ed665317f2
config is a command published in the GitHub repository openclaw/Peekaboo (5,088 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,590 tokens. A static security scan graded it D with 2 findings (asks the agent to reveal its instructions, harvests environment variables). 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.