← Back to Skills Marketplace
701
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-cost-governor
Description
Pre-flight cost estimation for subagent spawns and approval gates. Prevents API overspend and surprise billing. Budget control for sessions_spawn calls. Dail...
Usage Guidance
This skill appears to do exactly what it claims: estimate costs, require approval over a small threshold, and log to a workspace note. It does not request secrets or reach out to remote endpoints. Before installing: 1) Review the included JS files (lib/cost-tracker.js, bin/cost-summary.js) yourself — they operate on ~/.openclaw/workspace and append/update cost-tracking.md; 2) Back up or create a dedicated workspace path to avoid accidental writes to other notes; 3) Prefer configuring budget via the workspace .env or skill config rather than blindly pasting enforcement text into your global system prompt — changing system prompts is powerful and can affect other agent behavior; 4) If you enable cron jobs or automated invocation, test the scripts manually first (run node bin/cost-summary.js --daily) to confirm behavior; 5) If you want stricter guarantees, require manual approval (do not allow autonomous agent invocations) or lower the approval threshold. Overall, the package is coherent and low-risk, but exercise normal caution when allowing automated changes to prompts or adding scheduled tasks.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-cost-governor
Version: 1.0.0
The OpenClaw Cost Governor skill bundle is benign. All code and instructions are clearly aligned with its stated purpose of cost estimation, tracking, and approval for subagent spawns. File operations are confined to the skill's designated `cost-tracking.md` file within the OpenClaw workspace. Setup commands in `SKILL.md` and `README.md` involve creating directories, files, and setting environment variables within the workspace, or scheduling the skill's own scripts via `openclaw cron`, which are standard and expected for skill functionality. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent for harmful purposes. Minor regex vulnerabilities (ReDoS) are potential flaws but do not indicate malicious intent.
Capability Assessment
Purpose & Capability
Name/description align with what the skill does: estimation functions, logging to a workspace note, and a CLI summary. The included JS libraries (cost-tracker, cost-summary) are exactly what you'd expect for this functionality. No unrelated binaries, services, or credentials are requested.
Instruction Scope
Instructions direct the agent to estimate costs, write/read the workspace tracking file (~/.openclaw/workspace/notes/cost-tracking.md), optionally set DAILY_BUDGET in a workspace .env, and integrate with sessions_spawn and cron. This stays within the stated purpose. One notable item: the SKILL.md suggests adding a budget line to the system prompt to enforce stops ("Daily API budget: $XX. Stop spawning subagents if estimated total exceeds this"). A static scanner flagged that pattern as 'system-prompt-override' — in this context it appears to be a user-facing recommendation to put budget guidance in the system prompt (which is a plausible operational approach) but modifying the system prompt is powerful and should be done intentionally.
Install Mechanism
There is no remote install step or download URL; the package is instruction+local JS files. That is low risk compared to remote installation. The included scripts are plain Node.js and operate on local files; no external network calls or downloads are present in the code.
Credentials
The skill requests no credentials or environment variables. It suggests writing a DAILY_BUDGET to a workspace .env as an optional convenience — this is proportional for a budget-enforcement tool. It reads and writes files in the user's workspace only (no access to system-wide credentials or unrelated config paths).
Persistence & Privilege
always is false and the skill can be invoked autonomously (default). It does not request permanent elevated privileges, does not modify other skills' config, and does not write to system-wide settings beyond user workspace files and optional cron entries (cron addition is user-driven in README).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-cost-governor - After installation, invoke the skill by name or use
/openclaw-cost-governor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Cost governance skill for OpenClaw multi-agent deployments.
- Adds pre-flight cost estimation before subagent spawns to prevent API overspend.
- Implements approval gates for tasks estimated over $0.50.
- Tracks and logs all session spawn costs for daily budget control.
- Uses historical multipliers and real model rates for more accurate cost estimates.
- Provides tools for daily/monthly spend summaries and post-task reconciliation.
- Budget cap alerts and prevents further spawns when exceeded.
Metadata
Frequently Asked Questions
What is Cost Governor - Subagent Budget Control?
Pre-flight cost estimation for subagent spawns and approval gates. Prevents API overspend and surprise billing. Budget control for sessions_spawn calls. Dail... It is an AI Agent Skill for Claude Code / OpenClaw, with 701 downloads so far.
How do I install Cost Governor - Subagent Budget Control?
Run "/install openclaw-cost-governor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Cost Governor - Subagent Budget Control free?
Yes, Cost Governor - Subagent Budget Control is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Cost Governor - Subagent Budget Control support?
Cost Governor - Subagent Budget Control is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Cost Governor - Subagent Budget Control?
It is built and maintained by dp-del (@donovanpankratz-del); the current version is v1.0.0.
More Skills