sync-upstream

sync-upstream is a skill for Claude Code, Codex from ric03uec/clawrium. It costs 35 tokens per session (4,653 once invoked), scanned A, original, Apache-2.0.

A maintenance workflow that compares pinned versions of the Hermes, OpenClaw, and ZeroClaw agents with their latest stable upstream releases. Upstream means the original projects where new versions are published.

In plain words
What is it for?
Use it to check release feeds and open GitHub tracking issues when upgrades are available. It creates one overall issue and one issue for each agent with a version gap.
Why use it?
It shows maintainers when the repository is using an older stable agent version without changing local configuration or running agents.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ric03uec/clawrium/sync-upstream
Any agent
npx skills add ric03uec/clawrium --skill sync-upstream
Clone the repo
git clone --depth 1 https://github.com/ric03uec/clawrium

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sync-upstream

README.md
[![agentmods](https://agentmods.dev/badge/skills/ric03uec/clawrium/sync-upstream.svg)](https://agentmods.dev/skills/ric03uec/clawrium/sync-upstream)
Your own site
<a href="https://agentmods.dev/skills/ric03uec/clawrium/sync-upstream"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/sync-upstream.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.04653
Opus 5 $0.00017 $0.02327
Sonnet 5 $0.00007 $0.00931
Haiku 4.5 $0.00003 $0.00465

Measured today against content hash 6de9ccb42ab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

.claude/skills/sync-upstream/SKILL.md · 332 lines

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:

  1. the highest version currently pinned in src/clawrium/platform/registry/<type>/manifest.yaml
  2. the latest stable (non-prerelease, non-beta, non-alpha) upstream version
  3. whether (2) is newer than (1)

When (2) > (1) for at least one agent, open:

  • One parent issue titled upstream agent upgrade YYYY-MM-DD that 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 of hermes, 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:

  1. 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 as upstream-rejected: <agent> and treat the agent as "upstream-unreachable" for this run.
  2. Strip a single leading v only if present (hermes / zeroclaw tags); never lstrip("v") (would mangle a hypothetical vvv1.0).
  3. After validation, pass through cli/output/_sanitize.py:sanitize_passthrough for any value rendered to the terminal, matching the workspace-overlay path's contract.

Read the full file on GitHub · 332 lines

Changes

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.

  1. today Changed 6de9ccb42ab5
  2. 4d ago First seen · 332 lines · 35 tokens per session scan A 848df2232076

Subscribe to this mod's changes

sync-upstream is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 4,653 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.