skill-sync

A skill for managing locally imported skills that come from known Git repositories. Git is a system for tracking file changes and sharing code between versions.

In plain words
What is it for?
Use it to import, inspect, compare, update, pin, reset, publish, remove, and copy managed skills to enabled coding clients.
Why use it?
It helps keep imported skills aligned with their source while preserving local edits and showing differences or conflicts.

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/conn-castle/agent-layer/skill-sync
Any agent
npx skills add conn-castle/agent-layer --skill skill-sync
Clone the repo
git clone --depth 1 https://github.com/conn-castle/agent-layer

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 944 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 $0.00063 $0.00944
Opus 5 $0.00032 $0.00472
Sonnet 5 $0.00013 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 2d ago against content hash c059c06dfbdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 2d 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.

internal/templates/skills-catalog/skill-sync/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Sync

Use this skill to import known skills from Git and manage them over time. Users can edit imported skills locally, pull upstream updates without overwriting those edits, pin imports to a chosen version, reset them to upstream, or publish changes back.

Use live al skills --help and subcommand help as the source of truth. If al is unavailable or the project is not initialized, stop and report the error. Do not replace an al skills operation with manual file edits.

There is no al skills sync command. Use al skills pull to update skills from Git. Use al sync only to copy the current local skills into enabled client directories.

  1. Start with al skills status --all. It reads local state without using the network. A conflicted skill includes its Git workspace path.
  2. To compare live trees, run al skills diff <name> with --from/--to base, local, upstream, or destination. Defaults are local to upstream. The output is an ordinary Git unified diff.
  3. To import skills, run al skills add <repository> <selector>... --yes only when the user explicitly requests the import and the repository and selectors are known. Quote selectors that contain wildcards or start with !. The command does not search for, recommend, or preview skills. Run al skills add --help before choosing source, tracking, or publishing options.
  4. To update imported skills, run al skills pull. It fetches every configured source and merges upstream changes with local edits. Pinned imports stay at their locked versions unless their configured ref changes. Treat any partial or conflicted result as a failure and report every result. For a conflict, finish the Git merge in the workspace named in the error, git add the result, then run al skills resolve <name>. Do not hand-edit the lockfile.
  5. To stop managing one selector, run al skills remove <repository> <selector> --yes only when the user explicitly requests the removal, using the exact values from .agent-layer/config.toml. Skills still matched by another selector remain managed. Clean skills that are no longer matched are deleted. If one has local edits, the command fails and preserves it. Removing an exclusion may import newly included skills.

Edit an imported skill only in .agent-layer/skills-imported/<skill-name>/. Do not edit the generated copies under .agents/skills/ or .claude/skills/. The al sync command replaces them.

Read the full file on GitHub · 77 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. 2d ago First seen · 77 lines · 63 tokens per session scan A c059c06dfbdb

Subscribe to this mod's changes

skill-sync is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 944 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories