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 agentmods add skills/khaledsaeed18/dotclaude/create-agentnpx skills add KhaledSaeed18/dotclaude --skill create-agentgit clone --depth 1 https://github.com/KhaledSaeed18/dotclaudeWhat 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 | $0.00071 | $0.01211 |
| Opus 5 | $0.00036 | $0.00606 |
| Sonnet 5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
create-agent 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a subagent that earns its own context window: one clear role, a tightly curated tool allowlist, and a system prompt focused enough that the main agent knows exactly when to delegate to it. Then regenerate the derived files and validate.
Source layout is agents/<category>/<name>/AGENT.md. Agents are file-layout: the folder must contain only AGENT.md, because it installs as the single file .claude/agents/<name>.md. The category is the folder; the per-agent registry.json, the root registry.json, and the README catalog are all generated by pnpm gen. Never hand-edit generated files.
Hard rules: never break these
- One agent, one role. A subagent exists to keep a side task out of the main context and return a tight result. If the role needs "and" to describe it, narrow it or split it.
- Curate the tool allowlist ruthlessly. The whole point of a subagent is a constrained tool set. Grant only what the role genuinely needs; omit
Bashunless it must run commands, omit write tools for a read-only reviewer. Inheriting everything defeats the purpose. - File layout: only
AGENT.md. No companion files in an agent folder.pnpm genrejects extra files because the agent installs as one file. Reference material for the agent goes in its system prompt, not a sidecar. nameis globally unique and equals the folder name, kebab-case. Agents install to a flat.claude/agents/<name>.md.- Never hand-write
registry.jsonor the README catalog. They are derived; runpnpm gen. - No AI/co-author mentions anywhere in the agent or in what it produces.
Step 1: Define the agent
Pin down before writing a line:
- The one role, in a sentence.
- When the main agent should delegate to it. This is the most load-bearing decision; it drives the
description. - The tools the role actually needs. List them; everything else stays off.
- The model.
opusfor synthesis and hard judgment,haikufor cheap high-volume work,inherit(the default) when it should match the session.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 78 lines · 71 tokens per session scan A ee0d0be898b9
create-agent is a skill published in the GitHub repository KhaledSaeed18/dotclaude (4 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 1,211 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 2026-08-31.
Other skills, from other repositories
release
Cut a new playback-mcp release — version bump, changelog, dev-to-main PR, tag, and npm publish via CI. Use when asked to plan or ship a new release/version.
pr
Open a pull request from dev into main for this repo, following the repo's checklist and template. Use when asked to open/create a PR, or as part of the release flow.
pyenv-native
Manages Python runtimes and project venvs via pyenv-native and pyenv-mcp. Use when installing Python, fixing which-python/venv issues, setting .python-version, pip env problems on Windows/Linux/macOS, or when MCP pyenv-native tools are available.
rpg
Build and query semantic code graphs using RPG-Encoder. Use BEFORE grep/cat/find for any question about code structure, behavior, relationships, impact, dependencies, or cross-file patterns.
src
use when generating a doc the user will read and share — specs, roadmaps, pr explainers, research reports, plans, strategy docs. trigger words: "glyph," "spec," "roadmap," "explainer," "report," "plan," "save as a doc.".
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.