Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AKSoftCode/aicrewnpx agentmods add commands/aksoftcode/aicrew/update-skillsWrote 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/commands/aksoftcode/aicrew/update-skills)<a href="https://agentmods.dev/commands/aksoftcode/aicrew/update-skills"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/update-skills/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/commands/aksoftcode/aicrew/update-skills"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/update-skills.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 | $0.00015 | $0.02338 |
| Opus 5.5 | $0.00006 | $0.00935 |
| Sonnet 5.5 | $0.00003 | $0.00468 |
| Haiku 4.5 | $0.00002 | $0.00234 |
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 1mo 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 — 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 AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity 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 waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous 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?
- Update global skills — review and refresh
~/.claude/skills/- Generate project skills — analyze this project, create
.ai/skills/add-ons- Internet research — find new best practices, skills, agents to add or replace
- Full evolution — all three in sequence
- Review only — audit what exists, show gaps, no writes
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.
- 1mo ago First seen · 295 lines · 15 tokens per session scan A 3dc8b8796a58
update-skills is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 2,338 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 2026-08-31.
Other commands, from other repositories
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
clarify
Pre-plan interview — resolves spec ambiguity (v0.1 contract), pins the architectural lurkers from .specify/knowledge/architectural-lurkers.yaml, fires trigger-driven probes from .specify/knowledge/triggers.yaml, walks compliance scope, and writes decisions to specs/defaults/registry.yaml with provenance tagging.
specify
Create or update the feature specification from a natural language feature description.
registry
Discover, create, or update the Project Defaults Registry. Scans project manifests (package.json, pyproject.toml, Cargo.toml, go.mod, etc.), batches findings for HITL confirmation, then writes specs/defaults/registry.yaml with a full audit trail in changelog.md.