agent-kernel: Skill for Claude Code

.agents/skills/ak-dev-sync-skills-from-branch/SKILL.md

ak-dev-sync-skills-from-branch is a skill for Claude Code, Codex from yaalalabs/agent-kernel. It costs 72 tokens per session (1,903 once invoked), scanned A, original, Apache-2.0.

A maintenance guide for updating Agent Kernel's contributor and user instructions after code changes are made on a branch.

In plain words
What is it for?
Use it to inspect branch changes, update or add skills, remove obsolete guidance, and keep related catalogs and evaluations consistent.
Why use it?
It helps keep documented workflows and listed capabilities aligned with the actual implementation before a feature or fix is merged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is yaalalabs/agent-kernel's own configuration. It tells Claude Code and Codex how to work on agent-kernel 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 agent-kernel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yaalalabs/agent-kernel. 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/yaalalabs/agent-kernel/develop/.agents/skills/ak-dev-sync-skills-from-branch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yaalalabs/agent-kernel

Made for: Claude Code, Codex.

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 ak-dev-sync-skills-from-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch/github.svg)](https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch)
Your own site
<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch/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 ak-dev-sync-skills-from-branch

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-from-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,903 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00072 $0.01903
Opus 5 $0.00036 $0.00951
Sonnet 5 $0.00014 $0.00381
Haiku 4.5 $0.00007 $0.00190

Measured today against content hash fc62672d7ab2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ak-dev-sync-skills-from-branch 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 today.

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.

.agents/skills/ak-dev-sync-skills-from-branch/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Skills From Branch Changes

Use this skill when a feature branch or bugfix branch is functionally ready and you need to align Agent Kernel's skills with what actually changed.

This skill is for skill maintenance driven by code diff, not for implementing the feature itself.

Goal

Read the branch delta, infer what contributor-facing and user-facing capabilities changed, then:

  • update existing developer skills under .agents/skills/
  • add new developer skills if a new reusable contributor workflow now exists
  • update existing user skills under ak-py/src/agentkernel/skills/
  • add new user skills if a new reusable end-user workflow now exists
  • remove obsolete skills only when the codebase no longer supports that capability and no replacement path remains
  • update evals and skill catalogs/docs so the inventory remains consistent

When to Use This Skill

Use this skill when all of the following are true:

  1. The developer is on a feature or bugfix branch.
  2. The implementation is already done or nearly done.
  3. There are new commits on the branch and/or uncommitted local changes.
  4. The change may affect capabilities, workflows, supported integrations, deployment paths, contributor workflows, or examples.

Do not use this skill as the first step of a feature. Use it near the end, before merge or PR finalization.

Step 1: Determine the Comparison Base

Find the correct baseline branch first.

Preferred order:

  1. The PR target branch if it is known.
  2. The upstream tracking branch for the current branch.
  3. origin/develop.
  4. develop.

For this repository, prefer origin/develop or develop as the default base branch unless the PR target or upstream tracking branch says otherwise.

Use Git to identify the merge base between the current branch and that baseline.

Minimum evidence to gather:

  • current branch name
  • merge base commit
  • commits since merge base
  • staged changes
  • unstaged changes

If the baseline is ambiguous, state the assumption you are using and continue.

Read the full file on GitHub · 236 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. today Changed · +2 lines fc62672d7ab2
  2. 9d ago First seen · 234 lines · 72 tokens per session scan A 506c02c0c6b0

Subscribe to this mod's changes

ak-dev-sync-skills-from-branch is a skill published in the GitHub repository yaalalabs/agent-kernel (166 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,903 once invoked, about $0.0004 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.