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 ric03uec/clawrium --skill release-announcementsgit clone --depth 1 https://github.com/ric03uec/clawriumWrote 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/ric03uec/clawrium/release-announcements)<a href="https://agentmods.dev/skills/ric03uec/clawrium/release-announcements"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/release-announcements/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ric03uec/clawrium/release-announcements"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/release-announcements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 40 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00024 | $0.03361 |
| Opus 5 | $0.00012 | $0.01681 |
| Sonnet 5 | $0.00005 | $0.00672 |
| Haiku 4.5 | $0.00002 | $0.00336 |
Grade A, and why
clawrium-release-announcements 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clawrium-release-announcements
Once per day, check ric03uec/clawrium on GitHub for new releases. For each
release that has not yet been processed, draft a release blog post, open a PR,
post a Discord announcement, and enter an iteration loop: poll the PR for new
comments every 30 minutes, address feedback, and only complete when the PR is
merged. Skip releases whose tag range contains zero commits (re-tags).
Silent operation: When running as a scheduled job, if there are no new
releases to process and no new PR comments to address, respond with [SILENT]
to suppress delivery. Do not send "no updates found" notifications.
When to Use
- Triggered by a daily cron that sends a "check for new clawrium releases" request to the agent.
- Triggered ad-hoc by an operator request such as
"check
ric03uec/clawriumfor new releases" or "produce a release announcement forv<version>".
Do not run this skill more than once per release tag — the procedure is idempotent (it re-queries GitHub and kanban for existing artifacts before writing), but the intent is one announcement per release.
Quick Reference
| Phase | Action |
|---|---|
| Discover | gh release list --repo ric03uec/clawrium --limit 10; filter unprocessed tags |
| Triage | git log <prev_tag>..<tag> — skip if zero commits; classify the rest |
| Draft | Write blog markdown per skills/clawrium/blog-author/SKILL.md rules |
| PR | Create branch blog/<tag>-<slug>, commit file, push, open PR |
| Discord | Post short announcement in #announcements |
| Iterate | Poll PR comments + review comments every 30 min, apply feedback, push fixes |
| Complete | Move kanban task to Done once PR is merged; record tag in memory |
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.
- 9d ago First seen · 395 lines · 24 tokens per session scan A 334069894416
clawrium-release-announcements is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 3,361 once invoked, about $0.0001 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
python
Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…
perseus
Use when you need a bounded, local Perseus context render before an assistant reads project state. Perseus resolves selected workspace inputs such as git, services, sessions, and task notes into markdown. Use for deterministic session starts, workspace audits, and explicit context handoffs.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
metagit-cli
CLI-only shortcuts for metagit agents — workspace catalog, discovery, prompts, sync, layout, and config. Use instead of MCP or HTTP API when operating from a shell or agentmode session.
metagit-context-pack
Token-efficient workspace onboarding via tiered context packs — map, repo cards, session digest, objectives, approvals, repomix profiles. Use at session start or when scoping work in a metagit-managed workspace.
metagit-projects
Ongoing workspace and project management for OpenClaw and Hermes agents. Use when starting work, organizing repos, or before creating a new project folder so existing metagit projects are reused instead of duplicated.