ClawHub is a public registry where OpenClaw users publish, version, search, and install text-based agent skills and OpenClaw packages. It provides web browsing, a CLI-oriented API, moderation, vector search, and artifact hosting for code plugins, bundle plugins, and experimental whole-agent packages. The catalogue skills and agents are entries that can be discovered or used through this registry.
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 skills add openclaw/clawhub --skill controlling-costsgit clone --depth 1 https://github.com/openclaw/clawhubWrote 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/openclaw/clawhub/controlling-costs)<a href="https://agentmods.dev/skills/openclaw/clawhub/controlling-costs"><img src="https://agentmods.dev/badge/skills/openclaw/clawhub/controlling-costs.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 | $0.00050 | $0.01808 |
| Opus 5 | $0.00025 | $0.00904 |
| Sonnet 5 | $0.00010 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade B, and why
controlling-costs 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 7d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Run any script with `-h` for full usage Copies of this mod
1 near-identical copy found in the catalogue:
- controlling-costs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Axiom Cost Control
Dashboards, monitors, and waste identification for Axiom usage optimization.
Before You Start
-
Load required skills:
skill: axiom-sre skill: building-dashboardsBuilding-dashboards provides:
dashboard-list,dashboard-get,dashboard-create,dashboard-update,dashboard-delete -
Find the audit dataset. Try
axiom-auditfirst:['axiom-audit'] | where _time > ago(1h) | summarize count() by action | where action in ('usageCalculated', 'runAPLQueryCost')- If not found → ask user. Common names:
axiom-audit-logs-view,audit-logs - If found but no
usageCalculatedevents → wrong dataset, ask user
- If not found → ask user. Common names:
-
Verify
axiom-historyaccess (required for Phase 4):['axiom-history'] | where _time > ago(1h) | take 1If not found, Phase 4 optimization will not work.
-
Confirm with user:
- Deployment name?
- Audit dataset name?
- Contract limit in TB/day? (required for Phase 3 monitors)
-
Replace
<deployment>and<audit-dataset>in all commands below.
Tips:
- Run any script with
-hfor full usage - Do NOT pipe script output to
headortail— causes SIGPIPE errors - Requires
jqfor JSON parsing - Use axiom-sre's
axiom-queryfor ad-hoc APL, not direct CLI
Which Phases to Run
| User request | Run these phases |
|---|---|
| "reduce costs" / "find waste" | 0 → 1 → 4 |
| "set up cost control" | 0 → 1 → 2 → 3 |
| "deploy dashboard" | 0 → 2 |
| "create monitors" | 0 → 3 |
| "check for drift" | 0 only |
Phase 0: Check Existing Setup
# Existing dashboard?
dashboard-list <deployment> | grep -i cost
# Existing monitors?
axiom-api <deployment> GET "/v2/monitors" | jq -r '.[] | select(.name | startswith("Cost Control:")) | "\(.id)\t\(.name)"'
If found, fetch with dashboard-get and compare to templates/dashboard.json for drift.
Phase 1: Discovery
scripts/baseline-stats -d <deployment> -a <audit-dataset>
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 2.1 KB
- reference/analysis-report-template.md 3.1 KB
- reference/dashboard-panels.md 3.7 KB
- reference/monitor-strategy.md 13 KB
- scripts/analyze-query-coverage 22 KB
- scripts/baseline-stats 8.2 KB
- scripts/create-monitors 15 KB
- scripts/deploy-dashboard 3.6 KB
- scripts/lib/ast-parser.jq 7.6 KB
- scripts/lib/format-bytes.sh 2.5 KB runs code
- scripts/list-notifiers 2.2 KB
- scripts/setup 3.4 KB
- scripts/test-ast-parser 25 KB
- templates/dashboard.json 25 KB
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.
- 7d ago First seen · 233 lines · 50 tokens per session scan B a0823b1b1581
controlling-costs is a skill published in the GitHub repository openclaw/clawhub (9,399 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,808 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
directory-based-skill
A skill loaded from a directory structure with SKILL.md frontmatter, plus file-based and URL-based instruction sources.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
unity-dotween
Automate DOTween Free/Pro at editor time.
unity-architecture
Advise on Unity gameplay and system architecture.
unity-profiler
Capture read-only Unity runtime performance snapshots.