OPOS: Skill for Claude Code

.claude/skills/sync-from-core/SKILL.md

sync-from-core is a skill for Claude Code from Koroqe/OPOS. It costs 26 tokens per session (2,515 once invoked), scanned C, original, MIT.

A controlled update process that applies changes from an upstream Copier template to a local repository.

In plain words
What is it for?
Use it after an update check finds a newer version, or to preview changes without modifying files. It creates an update branch and requires a clean working tree.
Why use it?
It prevents upstream changes from being mixed with uncommitted local work and lets you inspect the differences before committing them.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions subagents.

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 shared/scripts/verify-sync.mjs --rev FETCH_HEAD # --from defaults to the parent's pin.

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/sync-from-core/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 sync-from-core

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/koroqe/opos/sync-from-core"><img src="https://agentmods.dev/badge/skills/koroqe/opos/sync-from-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,515 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00026 $0.02515
Opus 5.5 $0.00010 $0.01006
Sonnet 5.5 $0.00005 $0.00503
Haiku 4.5 $0.00003 $0.00251

Measured 27d ago against content hash 654dcd891563, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

sync-from-core scanned grade C with 1 finding 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 27d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

wsl -- bash -lc 'rm -rf ~/opos-sync && git clone -q /mnt/<drive>/<path-to-repo> ~/opos-sync && cd ~/opos-sync \
.claude/skills/sync-from-core/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sync-from-core

When to use

Manually, after check-for-updates reports a new version is available. Or unconditionally to pull the latest upstream changes.

Run it in a subagent, never in the interactive main thread (v0.21.0). A sync reads and diffs many files; done inline, all of that output stays in the conversation, and every later request re-reads it. Measured at a consumer: a sync run inside a 450k–900k-token session was the bulk of the 183M tokens its usage dashboard attributed to check-for-updates. Routine releases are applied by the daily SessionStart updater (opos-session-update.mjs), so a manual sync should be rare. When one is needed, apply every pending release in one run, not one run per release.

Inputs

  • target_version (optional; default: latest non-prerelease release tag from upstream).
  • branch (optional; default: opos-update-<tag>).
  • check_only (optional bool; default false): if true, runs copier update --dry-run and prints the diff without creating a branch or modifying files. Useful for previewing changes.

Steps

  1. Resolve repo root via git rev-parse --show-toplevel. Ensure the working tree is clean (git status --porcelain returns empty). If not: ABORT with instruction to commit or stash first. Do NOT proceed with a dirty tree — copier update would mix consumer's in-progress edits with upstream changes.
  2. Read <repo-root>/.copier-answers.yml. Extract _src_path. Classify it with the same four-shape logic as check-for-updates step 4 (remote GitHub → <owner>/<repo>; existing local clone → warn "local path, non-portable" and resolve tags via git -C <path> tag; missing local path or unparseable → ABORT with: _src_path '<value>' cannot be used for updates on this machine. Edit .copier-answers.yml and set _src_path to gh:<owner>/<repo> (leave _commit untouched), commit, and re-run.). If .copier-answers.yml is missing: ABORT with instruction to scaffold via copier copy first (this skill cannot bootstrap a repo).
  3. Resolve target_version:
    • If --target_version passed: use it.
    • Else (remote shape): gh api repos/<owner>/<repo>/releases --jq '[.[] | select(.prerelease == false)] | first | .tag_name' (no leading slash — MSYS/Git-Bash path-mangling on Windows). Local-clone shape: git -C <path> tag --sort=-v:refname | grep -v -- '-' | head -1.
  4. If --check_only is true (v0.8.1 rewrite — Copier has no --dry-run, and --pretend is ignored by copier update's patch-apply step, so a real preview needs a throw-away branch): git checkout -b opos-preview-<tag> → copier update --vcs-ref <tag> --defaults --conflict rej → print git status --porcelain (flag .rej files) and git diff --stat → git reset --hard && git clean -fd → git checkout - → git branch -D opos-preview-<tag>. Nothing is committed and the tree is left exactly as found. Skip steps 5–9.
  5. Create the update branch: git checkout -b <branch> (default opos-update-<tag>). 5b. Record the current pin as OLD_PIN (_commit in .copier-answers.yml) — step 6c needs it.

Read the full file on GitHub · 101 lines

Files

What ships with it

2 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. 27d ago Changed · +12 lines scan A → C 654dcd891563
  2. 28d ago Changed · +15 lines b812a4741384
  3. 1mo ago Changed · +12 lines 77da975888ee
  4. 1mo ago First seen · 62 lines · 26 tokens per session scan A 7e1abc3d0bfb

Subscribe to this mod's changes

sync-from-core is a skill published in the GitHub repository Koroqe/OPOS (4 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 2,515 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.