skills

A project command that lists registered SkDD skills and compares them with skill files on disk. SkDD appears to be the project's system for managing these skills.

In plain words
What is it for?
Use it to list all active skills or filter them by name or description, and to find unregistered or missing skill files.
Why use it?
It helps you see which skills are available, missing, or not recorded in the project registry without checking several files manually.

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/zakelfassi/skills-driven-development/skills
Clone the repo
git clone --depth 1 https://github.com/zakelfassi/skills-driven-development
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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 $0.00009 $0.00516
Opus 5 $0.00005 $0.00258
Sonnet 5 $0.00002 $0.00103
Haiku 4.5 $0.00001 $0.00052

Measured 3d ago against content hash 615054cefe5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

plugins/skdd-claude/commands/skills.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/skills

You are being asked to list the skills available in this project's SkDD colony.

What the user typed

/skills $ARGUMENTS

Your task

  1. Look for the colony registry in this order:
    • .skills-registry.json at the project root (machine-readable)
    • .skills-registry.md at the project root (human-readable)
    • If neither exists, report: "No SkDD colony detected. Run skdd init (if you have the CLI) or see docs/integrations/claude-code.md for setup. No skills registered yet."
  2. Parse the registry. For each active skill, show: name, source, last-used (if present), uses (if present), and description.
  3. If $ARGUMENTS is non-empty, treat it as a case-insensitive filter — only show skills whose name or description contains the filter string.
  4. Also list the skills actually present on disk under .claude/skills/ (or whichever plugin/scope provides them). If a skill is on disk but not in the registry, flag it as "unregistered — consider adding to .skills-registry.md". If a skill is in the registry but not on disk, flag it as "dangling — file missing".
  5. Format the output as a table with columns: Skill, Source, Status, Description. Use Markdown so it renders cleanly in Claude Code's chat.

What to do next

After listing, suggest one follow-up based on what you see:

  • If the registry is empty: suggest /forge <name> to create the first skill.
  • If there are unregistered skills on disk: suggest updating .skills-registry.md (offer to do it inline).
  • If there are dangling entries: suggest running skdd validate to clean them up, or ask whether to remove them.
  • If everything is tidy: suggest the user look for repeated work in the current session that could become a new skill.

Rules

  • Never invent skills that aren't in the registry or on disk.
  • Never modify the registry without asking first — listing is read-only by default.
  • If skdd CLI is available on the user's PATH, mention that they can also run skdd list from a terminal for a harness-agnostic view.

Read the full file on GitHub · 41 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. 3d ago First seen · 41 lines · 9 tokens per session scan A 615054cefe5f

Subscribe to this mod's changes

skills is a command published in the GitHub repository zakelfassi/skills-driven-development (18 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 516 once invoked, about $0.0000 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.