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/moazbuilds/claudeclaw/configgit clone --depth 1 https://github.com/moazbuilds/claudeclawWrote 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/commands/moazbuilds/claudeclaw/config)<a href="https://agentmods.dev/commands/moazbuilds/claudeclaw/config"><img src="https://agentmods.dev/badge/commands/moazbuilds/claudeclaw/config.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 | $0.00005 | $0.03248 |
| Opus 5 | $0.00003 | $0.01624 |
| Sonnet 5 | $0.00001 | $0.00650 |
| Haiku 4.5 | $0.00001 | $0.00325 |
Grade B, and why
config scanned grade B with 1 finding 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 4d 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.
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.
- Prompt: (show full prompt or "not set") How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
View or modify the heartbeat daemon settings. Use $ARGUMENTS to determine the action.
Parse $ARGUMENTS to identify what the user wants. If no arguments are given, show the current config.
Sub-commands
show (default when no arguments)
-
Read
.claude/claudeclaw/settings.json. -
Display all settings clearly:
General
- Model: (e.g.
opus,sonnet,haiku,glmor "default") - API token: (first 5 chars + "..." or "not configured"; used when
modelisglm) - Fallback model: (e.g.
glm,sonnet, or "not configured") - Fallback API token: (first 5 chars + "..." or "not configured")
- Timezone: (e.g.
America/New_Yorkor "UTC")
Heartbeat
- Enabled: yes/no
- Interval: Xm
- Prompt: (show full prompt or "not set")
- Exclude windows: (list each window's days + start-end, or "none")
- Forward to Telegram: yes/no (
HEARTBEAT_OKis forwarded only when enabled)
Telegram
- Token: (first 5 chars + "..." or "not configured")
- Allowed users: (list IDs or "none")
Security
- Level: (locked/strict/moderate/unrestricted)
- Allowed tools: (list or "default")
- Disallowed tools: (list or "none")
Web UI
- Enabled: yes/no
- Address: host:port
- Model: (e.g.
-
Also list any cron jobs from the configured jobs directory (see
jobsDirin settings, default:.claude/claudeclaw/jobs/) with their name, schedule, and notify mode. -
Remind the user that changes are hot-reloaded every 30s — no daemon restart needed.
heartbeat on / heartbeat off / heartbeat enable / heartbeat disable
Toggle the heartbeat on or off.
- Read
.claude/claudeclaw/settings.json. - Set
heartbeat.enabledtotrueorfalsebased on the command. - Write the updated settings back.
- Confirm the change.
heartbeat interval <minutes> / interval <minutes>
Change the heartbeat interval.
- Parse the number of minutes from
$ARGUMENTS. If not provided or invalid, use AskUserQuestion: "How often should the heartbeat run?" (header: "Interval", options: "5 minutes", "15 minutes (Recommended)", "30 minutes", "60 minutes") - Read
.claude/claudeclaw/settings.json. - Set
heartbeat.intervalto the new value. - Write the updated settings back.
- Confirm the change. The daemon will pick up the new interval within 30 seconds.
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.
- 4d ago First seen · 312 lines · 5 tokens per session scan B ab7a50ce7563
config is a command published in the GitHub repository moazbuilds/claudeclaw (1,315 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 3,248 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.