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.
npx skills add Szotasz/marveen --skill skill-managementgit clone --depth 1 https://github.com/Szotasz/marveenWrote 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/skills/szotasz/marveen/skill-management)<a href="https://agentmods.dev/skills/szotasz/marveen/skill-management"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/skill-management/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/skills/szotasz/marveen/skill-management"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/skill-management.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 | $0.00055 | $0.02012 |
| Opus 5 | $0.00028 | $0.01006 |
| Sonnet 5 | $0.00011 | $0.00402 |
| Haiku 4.5 | $0.00006 | $0.00201 |
Grade D, and why
skill-management scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
for dir in ~/.claude/skills/*/; do Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${HOME}/.claude/skills/${NAME}" How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Management -- CRUD for the Skill Library
When to use
- User asks "what skills do I have?" or "list skills"
- User wants to inspect a specific skill's content
- A
/retrospectiveproposes CREATE, PATCH, or DELETE actions on skills - User says "update skill X" or "fix skill Y"
- Periodic audit: check for stale or duplicate skills
Arguments
| Argument | Required | Description |
|---|---|---|
action |
YES | One of: list, show, create, patch, delete, audit |
name |
for show/patch/delete | Skill directory name (e.g. github-pr-rebase-merge) |
scope |
no | global (default, ~/.claude/skills/) or local (./claude/skills/) |
Examples:
/skills action=list-- list all skills with descriptions/skills action=show name=github-pr-rebase-merge-- show full SKILL.md/skills action=create name=new-skill-- interactive skill creation/skills action=patch name=existing-skill-- modify specific sections/skills action=delete name=old-skill-- remove with confirmation/skills action=audit-- find stale, duplicate, or oversized skills
Procedure
action=list
SKILL_DIR="${HOME}/.claude/skills"
if [ "$SCOPE" = "local" ]; then SKILL_DIR="./.claude/skills"; fi
echo "=== Skills in $SKILL_DIR ==="
for dir in "$SKILL_DIR"/*/; do
skill_file="$dir/SKILL.md"
if [ -f "$skill_file" ]; then
name=$(basename "$dir")
# Extract description from frontmatter
desc=$(sed -n '/^description:/{ s/^description: *//; p; q; }' "$skill_file")
printf " %-35s %s\n" "$name" "$desc"
fi
done
Present as a compact table. If both global and local exist, show both.
action=show
- Read
~/.claude/skills/{name}/SKILL.md - If it has a
references/subdirectory, list those files too - Present the full content
action=create
Interactive skill creation workflow:
- Ask for trigger context: "When should this skill activate?"
- Ask for procedure steps: "What does it do, step by step?"
- Generate SKILL.md with proper frontmatter:
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.
- 10d ago First seen · 236 lines · 55 tokens per session scan D 3163a5f72121
skill-management is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,012 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
oma-image
Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth), Antigravity (Gemini-family "nano-banana" image models via agy CLI + Gemini Code Assist; exact model chosen internally by agy), and Pollinations (flux/zimage, free with signup). Use for image…
oma-observability
Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics. Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident…
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
oma-db
Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model…
oma-design
AI design specialist skill with DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance. Covers typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2).