sync-upstream

A command that checks whether tracked Hermes, OpenClaw, or ZeroClaw agent versions are behind their upstream releases and can prepare related GitHub issues.

In plain words
What is it for?
Use it to check selected agent types, compare pinned versions with upstream releases, and—after explicit confirmation—open a parent issue with one child issue per agent.
Why use it?
It identifies outdated version pins while keeping the local manifest and running agents unchanged.

Command

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 commands/ric03uec/clawrium/sync-upstream
Clone the repo
git clone --depth 1 https://github.com/ric03uec/clawrium
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 240 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 $0.00031 $0.00240
Opus 5 $0.00015 $0.00120
Sonnet 5 $0.00006 $0.00048
Haiku 4.5 $0.00003 $0.00024

Measured 3d ago against content hash 7ee114513565, 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 3d 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.

.opencode/commands/sync-upstream.md · 23 lines

What it actually says

Run the upstream-version sync pass for tracked agent types.

$ARGUMENTS

See .opencode/skills/sync-upstream/SKILL.md for the full skill — it holds the upstream lookup commands (GitHub release list for hermes / zeroclaw, npm view openclaw dist-tags.latest for openclaw), the manifest-pin parser, the de-dup rules, and the parent + child issue body templates.

This command is read-only on the local repo and the running fleet — it never edits manifest.yaml, never restarts agents, never opens PRs. It only opens GitHub issues, and only after the user types the literal token open-issues at the confirmation prompt.

If $ARGUMENTS is non-empty, restrict the sync to the listed agent types — each token MUST match the allow-list {hermes, openclaw, zeroclaw} exactly. Any other value aborts the run.

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. 3d ago First seen · 23 lines · 31 tokens per session scan A 7ee114513565

Subscribe to this mod's changes

sync-upstream is a command published in the GitHub repository ric03uec/clawrium (51 stars, last pushed 15d ago), licensed Apache-2.0. It adds 31 tokens to every session and 240 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.