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 RongchangLi/pocketskill --skill share-skillgit clone --depth 1 https://github.com/RongchangLi/pocketskillWrote 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/rongchangli/pocketskill/share-skill)<a href="https://agentmods.dev/skills/rongchangli/pocketskill/share-skill"><img src="https://agentmods.dev/badge/skills/rongchangli/pocketskill/share-skill/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/rongchangli/pocketskill/share-skill"><img src="https://agentmods.dev/badge/skills/rongchangli/pocketskill/share-skill.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 | $0.00030 | $0.00942 |
| Opus 5.5 | $0.00012 | $0.00377 |
| Sonnet 5.5 | $0.00006 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
share-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 2mo 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 — 99 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 helping them share a skill to the community via GitHub PR.
Tool Expectations
This workflow may use git and gh commands.
All operations must happen from the pocketskill repository root. First locate it:
- Use the current working directory if it contains
plugins/my-skill/skills/. - Otherwise search upward from the current working directory.
- If no root is found, ask the user for the pocketskill path and stop until they provide it.
Workflow
1. Preflight
Run checks before listing or committing:
git rev-parse --is-inside-work-treemust succeed. If not, tell the user this directory is not a git repository and provide setup commands instead of continuing.git remote get-url originmust succeed. If not, stop and ask the user to add a GitHub remote.gh auth statusmust succeed before creating a PR. Ifghis missing or unauthenticated, still prepare the git commands but tell the user the exactgh auth login/gh pr createcommands to run manually.- Inspect
git status --short. Never use plaingit commitif unrelated staged changes exist.
2. Find Shareable Skills
Only share skills from plugins/my-skill/skills/my-skills/. Never share from private-skills/ or manage-skills/.
Rules:
- Include directories with untracked, modified, or staged changes shown by
git status --short -- plugins/my-skill/skills/my-skills. - Exclude
.DS_Store, editor files, cache files, and directories withoutSKILL.md. - Do not list unchanged skills unless the user explicitly asks to share an existing committed skill.
- If nothing is shareable, say so and stop.
Show the candidate names and ask the user to choose one or all.
3. Review Before Sharing
For every selected skill, review SKILL.md before committing:
- Frontmatter must include non-empty
nameanddescription. - Skill names must match
^[a-z0-9]+(-[a-z0-9]+)*$. - The body must contain real instructions, not just the template placeholder.
- Check for obvious secrets or private material: API keys, tokens, passwords, personal paths, private repo URLs, or private-skill references.
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.
- 2mo ago First seen · 99 lines · 30 tokens per session scan A 59dccf4bba94
share-skill is a skill published in the GitHub repository RongchangLi/pocketskill (2 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 942 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.
share-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| share-skillRongchangLi/pocketskill | Skill | 2 | 3mo ago | MIT | A | 30 | Claude Code |
| release-announcementpaperclipai/paperclip | Skill | 112k | today | MIT | A | 42 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 114k | today | Apache-2.0 | A | 13 | Claude Code |
| release-notesphuryn/pm-skills | Skill | 28k | 8d ago | MIT | A | 57 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 789 | 2d ago | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | today | Apache-2.0 | A | 22 | Claude Code, Codex |