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 spl-to-aplgit 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/spl-to-apl)<a href="https://agentmods.dev/skills/openclaw/clawhub/spl-to-apl"><img src="https://agentmods.dev/badge/skills/openclaw/clawhub/spl-to-apl.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01909 |
| Opus 5 | $0.00024 | $0.00955 |
| Sonnet 5 | $0.00010 | $0.00382 |
| Haiku 4.5 | $0.00005 | $0.00191 |
Grade A, and why
spl-to-apl 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- spl-to-apl — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SPL to APL Translator
Type safety: Fields like status are often stored as strings. Always cast before numeric comparison: toint(status) >= 500, not status >= 500.
Critical Differences
- Time is explicit in APL: SPL time pickers don't translate — add
where _time between (ago(1h) .. now()) - Structure: SPL
index=... | command→ APL['dataset'] | operator - Join is preview: limited to 50k rows, inner/innerunique/leftouter only
- cidrmatch args reversed: SPL
cidrmatch(cidr, ip)→ APLipv4_is_in_range(ip, cidr)
Core Command Mappings
| SPL | APL | Notes |
|---|---|---|
search index=... |
['dataset'] |
Dataset replaces index |
search field=value |
where field == "value" |
Explicit where |
where |
where |
Same |
stats |
summarize |
Different aggregation syntax |
eval |
extend |
Create/modify fields |
table / fields |
project |
Select columns |
fields - |
project-away |
Remove columns |
rename x as y |
project-rename y = x |
Rename |
sort / sort - |
order by ... asc/desc |
Sort |
head N |
take N |
Limit rows |
top N field |
summarize count() by field | top N by count_ |
Two-step |
dedup field |
summarize arg_max(_time, *) by field |
Keep latest |
rex |
parse or extract() |
Regex extraction |
join |
join |
Preview feature |
append |
union |
Combine datasets |
mvexpand |
mv-expand |
Expand arrays |
timechart span=X |
summarize ... by bin(_time, X) |
Manual binning |
rare N field |
summarize count() by field | order by count_ asc | take N |
Bottom N |
spath |
parse_json() or json['path'] |
JSON access |
transaction |
No direct equivalent | Use summarize + make_list |
Complete mappings: reference/command-mapping.md
Stats → Summarize
# SPL
| stats count by status
# APL
| summarize count() by status
Key function mappings
| SPL | APL |
|---|---|
count |
count() |
count(field) |
countif(isnotnull(field)) |
dc(field) |
dcount(field) |
avg/sum/min/max |
Same |
median(field) |
percentile(field, 50) |
perc95(field) |
percentile(field, 95) |
first/last |
arg_min/arg_max(_time, field) |
list(field) |
make_list(field) |
values(field) |
make_set(field) |
What ships with it
10 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.
- .meta/2026-01-28-schema-read-findings.md 3.4 KB
- .meta/cases.ts 5.7 KB runs code
- .meta/DESIGN-NOTES.md 6.4 KB
- .meta/spl-to-apl.eval.ts 4.2 KB runs code
- README.md 2.0 KB
- reference/command-mapping.md 7.3 KB
- reference/dataset-schemas.md 1.3 KB
- reference/examples.md 10 KB
- reference/function-mapping.md 11 KB
- tests/test-queries.md 4.3 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.
- 8d ago First seen · 260 lines · 48 tokens per session scan A 1be4db60184e
spl-to-apl is a skill published in the GitHub repository openclaw/clawhub (9,402 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,909 once invoked, about $0.0002 per session on Opus 5. 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 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.
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
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.