Borrowing it
Nothing to install: this file belongs to ric03uec/clawrium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ric03uec/clawrium/main/.claude/skills/sync-upstream/SKILL.mdgit 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/sync-upstream)<a href="https://agentmods.dev/skills/ric03uec/clawrium/sync-upstream"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/sync-upstream/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/sync-upstream"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/sync-upstream.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.04653 |
| Opus 5.5 | $0.00014 | $0.01861 |
| Sonnet 5.5 | $0.00007 | $0.00931 |
| Haiku 4.5 | $0.00003 | $0.00465 |
Grade A, and why
sync-upstream 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 1mo 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Upstream
Not to be confused with
clawctl agent sync. That command pushes config/workspace overlays to a running agent and rotates the gateway bearer (#437). This skill is read-only on the local repo and the running fleet — it only queries upstream release feeds and opens GitHub issues for the maintainer.
Recurring maintainer skill. For each tracked agent type (hermes, openclaw, zeroclaw), determine:
- the highest version currently pinned in
src/clawrium/platform/registry/<type>/manifest.yaml - the latest stable (non-prerelease, non-beta, non-alpha) upstream version
- whether (2) is newer than (1)
When (2) > (1) for at least one agent, open:
- One parent issue titled
upstream agent upgrade YYYY-MM-DDthat tracks the whole sync pass. - One child issue per agent with a gap, linked from the parent. Each child contains the upgrade plan AND the per-OS / per-arch test matrix inline as checklist rows — the test matrix is not broken out into grandchild issues.
This skill never edits manifest.yaml, never touches running agents, and never opens PRs. It only reads manifests, queries upstream, and creates issues.
Inputs
$ARGUMENTS(optional): one or more ofhermes,openclaw,zeroclaw. If empty, run all three.
$ARGUMENTS MUST be validated against the literal allow-list {hermes, openclaw, zeroclaw} before being interpolated into any filesystem path or shell command. A single unknown token aborts the run. This is a path-traversal guard — src/clawrium/platform/registry/<t>/manifest.yaml is the only place <t> is consumed, but the inline Python loop teaches the pattern and must not normalize an unsafe value.
Untrusted upstream strings
Every string returned by gh release list, npm view, or any other upstream feed is untrusted input. Before that value is rendered into an issue title, issue body, terminal report, or shell argument:
- Validate against the regex
^[A-Za-z0-9._+-]{1,40}$. Anything else (whitespace, control chars, bidi/zero-width codepoints, RTL overrides, unicode look-alikes) is rejected — log it asupstream-rejected: <agent>and treat the agent as "upstream-unreachable" for this run. - Strip a single leading
vonly if present (hermes / zeroclaw tags); neverlstrip("v")(would mangle a hypotheticalvvv1.0). - After validation, pass through
cli/output/_sanitize.py:sanitize_passthroughfor any value rendered to the terminal, matching the workspace-overlay path's contract.
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.
- 1mo ago Changed 6de9ccb42ab5
- 2mo ago First seen · 332 lines · 35 tokens per session scan A 848df2232076
sync-upstream is a skill published in the GitHub repository ric03uec/clawrium (67 stars, last pushed 13d ago), licensed Apache-2.0. It adds 35 tokens to every session and 4,653 once invoked, about $0.0001 per session on Opus 5.5. 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…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
telegram
Telegram Bot skill for sending and editing Telegram messages via Bot API. Use when Bub needs to: (1) Send a message to a Telegram user/group/channel, (2) Reply to a specific Telegram message with replytomessageid, (3) Edit an existing Telegram message, or (4) Push proactive Telegram notifications. Prefer rich…
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
modern-python-toolchain
Modern Python project setup with uv, ruff, and pyright. Use when initializing a new Python project, configuring the Python environment, setting up linting/formatting, or when a project needs uv (the fast Python package manager). Trigger on: 'set up Python', 'new Python project', 'configure uv', 'install uv', 'ruff'…
vexor-cli
Semantic file discovery via vexor. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing.