update-skills

A command for maintaining the skills used by coding agents. It can refresh shared skills or create project-specific skill overrides.

In plain words
What is it for?
Use it to update the shared skills system or add skills tailored to the current repository. It pauses for user decisions at required checkpoints.
Why use it?
It helps keep agent instructions current as a project or its working practices change.

Command

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 commands/aksoftcode/aicrew/update-skills
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,338 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 $0.00015 $0.02338
Opus 5 $0.00008 $0.01169
Sonnet 5 $0.00003 $0.00468
Haiku 4.5 $0.00002 $0.00234

Measured yesterday against content hash 3dc8b8796a58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-skills 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.

skills/commands/update-skills.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh or generate project-specific skills — updates ~/Agents/ globals or creates .ai/skills/ overrides for the current repo.

⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE

At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.

Known tools by platform (use if available):

Platform Checkpoint behavior
Claude Code Call AskUserQuestion tool if available; otherwise end response and wait
Cursor Call askFollowupQuestion tool if available; otherwise end response and wait
Antigravity Native ask tool if available; otherwise end response and wait
Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Codex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and wait
Autonomous script Stops execution — never invents your answer

NEVER skip a checkpoint. NEVER fabricate the user's response.

/update-skills — Skills Evolution Engine

You maintain and grow the skills system. You can refresh global skills, auto-generate project-specific skills from codebase analysis, and research the latest best practices from the internet to suggest additions or removals.

Step 0: Bootstrap (always runs first, silently)

Before anything else, run the setup script to ensure symlinks and hooks are registered:

bash ~/.claude/skills/setup.sh

If the current directory has a project skills layer, also run:

bash .ai/skills/setup.sh 2>/dev/null || true

This is idempotent — already-linked files are skipped. Report what was created vs already existed, then continue.


Step 1: Determine scope

If $ARGUMENTS is not provided, ask:

What would you like to do?

  1. Update global skills — review and refresh ~/.claude/skills/
  2. Generate project skills — analyze this project, create .ai/skills/ add-ons
  3. Internet research — find new best practices, skills, agents to add or replace
  4. Full evolution — all three in sequence
  5. Review only — audit what exists, show gaps, no writes

Read the full file on GitHub · 295 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. yesterday First seen · 295 lines · 15 tokens per session scan A 3dc8b8796a58

Subscribe to this mod's changes

update-skills is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 2,338 once invoked, about $0.0001 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.