Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add laurigates/claude-plugins/plugin install configure-pluginWrote 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/laurigates/claude-plugins/config-sync)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/config-sync"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/config-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.
<a href="https://agentmods.dev/skills/laurigates/claude-plugins/config-sync"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/config-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.02206 |
| Opus 5.5 | $0.00011 | $0.00882 |
| Sonnet 5.5 | $0.00006 | $0.00441 |
| Haiku 4.5 | $0.00003 | $0.00221 |
Grade A, and why
config-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 14d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/configure:config-sync
Extract, compare, and propagate tooling config improvements across FVH repos.
When to Use This Skill
| Use this skill when... | Use another approach when... |
|---|---|
| Comparing a workflow/config across all FVH repos | Configuring a single repo's workflow from scratch — use /configure:workflows |
| Propagating an improvement from one repo to many | Debugging a failing CI run — use github-actions-inspection |
| Identifying which repos have outdated configs | Creating a reusable workflow — use /configure:reusable-workflows |
| Extracting novel patterns from a repo to share | Checking a single repo's compliance — use /configure:status |
Context
- Workspace root:
/Users/lgates/repos/ForumViriumHelsinki - Repos: !
fd -t d -d 1 . /Users/lgates/repos/ForumViriumHelsinki --exclude .git --exclude node_modules - Current directory: !
pwd
Parameters
Parse mode and options from command arguments:
Modes
extract [repo-name]— Identify improvements in a source repodiff <file-pattern>— Compare a specific config across all reposapply <file-pattern> [--from repo] [--to repo1,repo2,...|--all]— Propagate config to targets
Options
--from <repo>— Source repo for apply mode (default: best version detected)--to <repo1,repo2,...>— Target repos (comma-separated)--all— Target all repos that have the file--dry-run— Show what would change without creating branches/PRs (default behavior)--confirm— Actually create branches and PRs
Config Categories
Tracked files fall into five sync tiers: Wholesale (copy verbatim: claude.yml, renovate.json), Parameterized (shared core + variation points), Structural (justfile recipe names), Pattern-based (Dockerfile*, by stack), and Reference (compare and report). Full file patterns, variation points, and stack detection: references/config-tiers.md — read it when classifying a file in Extract Step 3 or Apply Step 3.
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.
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.
- 14d ago Changed · -145 lines 7c3452d32bde
- 1mo ago First seen · 359 lines · 28 tokens per session scan A 0bb6f8e8d206
config-sync is a skill published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 2,206 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 2026-09-03.
Other skills, from other repositories
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
start-temps-cluster
Start (or restart) a local multi-node Temps cluster using Docker-in-Docker — one control plane + 3 worker nodes, each a privileged DinD container running its own dockerd + temps agent, wired with the real multi-host overlay (VXLAN, computecidr allocation) via tools/dev-cluster/ in whichever checkout/worktree you run…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.