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/rongchangli/pocketskill/create-skillnpx skills add RongchangLi/pocketskill --skill create-skillgit clone --depth 1 https://github.com/RongchangLi/pocketskillWhat 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 | $0.00031 | $0.01109 |
| Opus 5 | $0.00015 | $0.00554 |
| Sonnet 5 | $0.00006 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
create-skill 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
When the user invokes this skill, you are creating a new skill for their pocketskill library.
Skills are organized in three directories under plugins/my-skill/skills/:
my-skills/— user-created public skills (sharable)private-skills/— user-created private skills (gitignored)manage-skills/— built-in management skills (read-only, never create here)
Claude Code and Codex need a flat skills/<name>/SKILL.md plugin cache. Do not create files directly in that flat cache; install.sh exports it from these source directories during refresh.
First locate the pocketskill repository root:
- Use the current working directory if it contains both
plugins/my-skill/skills/andtemplates/SKILL.md.template. - Otherwise search upward from the current working directory for those two paths.
- If the repository root cannot be found, ask the user for the pocketskill path. Do not create files in an unrelated project.
Workflow
1. Ask Target Directory
Ask one question if the user did not already specify:
Where should this skill live?
1. my-skills — public, can be shared via PR to the community
2. private-skills — local only, never shared (gitignored)
Never offer manage-skills as a target. It is reserved for built-in management skills.
2. Collect And Validate Inputs
Ask for the skill name and one-line description if missing.
Validate the skill name before creating anything:
- Must match
^[a-z0-9]+(-[a-z0-9]+)*$ - Must not contain
/,\,.,.., spaces, shell metacharacters, or quotes - Must not collide with an existing skill name in
my-skills/,private-skills/, ormanage-skills/ - If invalid, explain the rule and ask again
Trim the description. If it is empty, ask again. Keep it short because it is used for auto-trigger matching.
3. Create The Skill Safely
Use this target path:
<repo-root>/plugins/my-skill/skills/<target-dir>/<skill-name>/SKILL.md
Where <target-dir> is my-skills or private-skills.
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 · 102 lines · 31 tokens per session scan A bcc41e19e24f
create-skill is a skill published in the GitHub repository RongchangLi/pocketskill (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,109 once invoked, about $0.0002 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.