OPOS: Skill for Claude Code

.claude/skills/auto-sync/SKILL.md

auto-sync is a skill for Claude Code from Koroqe/OPOS. It costs 42 tokens per session (6,461 once invoked), scanned A, original, MIT.

An automated routine for checking whether a new OPOS release is available and synchronizing it into another repository. OPOS appears to be the upstream project being copied into a consumer repository.

In plain words
What is it for?
Use it for scheduled or manual upstream synchronization, dry-run checks, automatic commits of clean updates, and escalation of conflicts through repository issues.
Why use it?
It removes the need to perform routine upstream checks and clean updates by hand. Clean synchronizations can be committed automatically, while conflicts are sent for human attention.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is Koroqe/OPOS's own configuration. It tells Claude Code how to work on OPOS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OPOS configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/skills/lease/lease.mjs acquire --key process:auto-sync --intent "scheduled OPOS sync" --ttl 30m.

View source ↗ Koroqe/OPOS
Reuse

Borrowing it

Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/auto-sync/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Koroqe/OPOS

Made for: Claude Code.

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 auto-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/koroqe/opos/auto-sync/github.svg)](https://agentmods.dev/skills/koroqe/opos/auto-sync)
Your own site
<a href="https://agentmods.dev/skills/koroqe/opos/auto-sync"><img src="https://agentmods.dev/badge/skills/koroqe/opos/auto-sync/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.

agentmods 80×15 button for auto-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/koroqe/opos/auto-sync"><img src="https://agentmods.dev/badge/skills/koroqe/opos/auto-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.06461
Opus 5.5 $0.00017 $0.02584
Sonnet 5.5 $0.00008 $0.01292
Haiku 4.5 $0.00004 $0.00646

Measured yesterday against content hash 774a883be17b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-sync 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 yesterday.

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/auto-sync/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-sync

When to use

As a scheduled routine (registered via /schedule-process auto-sync, daily cron 17 6 * * *) — the autonomous counterpart of sync-from-core. Also manually invokable as /auto-sync (e.g. to test the flow, or to pull an update immediately without the interactive review sync-from-core provides), or as /auto-sync --dry_run to see what a run would do without mutating anything.

The contract difference from sync-from-core is deliberate and absolute: sync-from-core waits for a human to review and commit; auto-sync commits clean syncs itself and escalates only when something needs a human. One skill cannot carry both postures — do not merge them.

Authority mapping

The scheduled-run prelude instructs: refuse any action not in the declared authority list. For this skill the declared list [commit, push, file_issue] maps to concrete actions as follows — every action below is inside the declaration:

  • commit — the full local mutation set needed to produce the sync commit: creating/deleting opos-auto-sync-<tag> work branches, the file writes performed by copier update, the CHANGELOG-only .rej auto-resolution (including deleting CHANGELOG.md.rej), refreshing .claude/.last-update-check, ff-merging the work branch to the default branch, and writing the run record.
  • push — git push of the ff-merged default branch, and of the work branch on the conflict path. On the cloud runtime, when the direct push is refused, the fallback of shared/cloud-integration.md (push the session's claude/* branch, open and merge a PR via REST) is the same integration act under commit + push; it needs no additional authority entry.
  • file_issue — gh issue create in the consumer's own repo (conflict, divergence, push-failure, and Action-mutual-exclusion escalations).

Anything outside this mapping (e.g. hand-editing files beyond the CHANGELOG rule, force-pushing, touching unrelated branches, writing to any other repo) is outside the declaration — refuse and record the refusal.

Read the full file on GitHub · 131 lines

Files

What ships with it

3 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.

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. yesterday Changed · +3 lines 774a883be17b
  2. 27d ago Changed · +3 lines 74c4ad5827b5
  3. 28d ago Changed · +16 lines 9003dfaf9efe
  4. 1mo ago Changed · +11 lines 45abc3bce10c
  5. 1mo ago First seen · 98 lines · 42 tokens per session scan A dbf661c6a56d

Subscribe to this mod's changes

auto-sync is a skill published in the GitHub repository Koroqe/OPOS (4 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 6,461 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

git-commit-integrity

Ensures every commit in a series is what it claims to be — a working, gate-passing snapshot in isolation, not just a slice of a working directory that happened to pass while other changes sat nearby. Covers verifying commit history after the fact, designing pre-commit hooks that check the commit rather than the…

irahardianto/awesome-agv · 136 tokens

workflow-solo

Single-agent feature pipeline with adaptive complexity. User-invoked entry point via /workflow-solo; not for autonomous or subagent use.

irahardianto/awesome-agv · 32 tokens

summarize-change-log

Condense long commit logs, squash messages, or change narratives into 1–5 GitHub-ready markdown bullets with Conventional Commit subjects (≤50 chars). Use when the user asks to summarize a git log, boil down commits, write a squash-merge message, or produce a five-bullet PR/merge summary.

CiscoDevNet/essentials · 70 tokens

pr-address-comments-all

Address GitHub PR review comments on one or more PRs in parallel, each in its own git worktree on the PR's branch, reusing the pr-address-comments procedure. Auto-starts (look up PRs, create worktrees, fetch comments), then pauses to show a per-PR addressing plan for approval; after approval each PR is handled by a…

CiscoDevNet/essentials · 169 tokens

sidecar

Use the sidecarsync CLI to read, update, and synchronize Sidecar notes or state in repos with .sidecar configurations. Covers peer selection, standalone repos, per-file rules, and fork recovery.

anteprojector/sidecar · 44 tokens

delivery

Fecha o ciclo de entrega local — build check, bump semântico, changelog e commit convencional. Deploy remoto somente sob a condição dupla do Ops. Use para "finalizar tarefa", "fazer release" ou "publicar versão".

rcelebrone/DotAgents · 50 tokens