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.
git clone --depth 1 https://github.com/rfxlamia/pockettoWrote 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/plugins/rfxlamia/pocketto/pocketto)<a href="https://agentmods.dev/plugins/rfxlamia/pocketto/pocketto"><img src="https://agentmods.dev/badge/plugins/rfxlamia/pocketto/pocketto/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/plugins/rfxlamia/pocketto/pocketto"><img src="https://agentmods.dev/badge/plugins/rfxlamia/pocketto/pocketto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pocketto 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 yesterday.
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.
What it actually says
{
"name": "pocketto",
"description": "Pocket-driven development skills: structured subagent delegation, bug hunting, iterative planning, code review workflows, and an opt-in education mentor mode for Claude Code.",
"version": "4.2.2",
"surface_manifest": "./surfaces.json",
"surfaces": {
"core": "claude/core",
"enterprise": "claude/enterprise"
},
"author": {
"name": "rfxlamia",
"url": "https://github.com/rfxlamia"
},
"repository": "https://github.com/rfxlamia/pocketto",
"keywords": ["pocket", "development", "delegation", "bug-hunting", "planning", "workflow", "structured-research", "education"]
}
What it installs
The manifest is a name and a version. 16 skills travel with it, and installing the plugin installs all of them — 1,211 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill pocket-development A 37 tokens
- Skill pocket-grinding A 65 tokens
- Skill pocket-planning A 76 tokens
- Skill pocket-closing A 71 tokens
- Skill create-pr A 66 tokens
- Skill pocket-education A 127 tokens
- Skill pocket-pitching A 109 tokens
- Skill validate-plan A 47 tokens
- Skill pocket-init A 72 tokens
- Skill structured-research A 147 tokens
- Skill bug-hunting A 46 tokens
- Skill pocket-enterprise A 28 tokens
- Skill pocket-help A 66 tokens
- Skill pocket-structuring A 43 tokens
- Skill hotfix A 65 tokens
- Skill brand-design B 146 tokens
What ships with it
1 file beside plugin.json 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.
- yesterday Changed 23fa6483202d
- 3d ago Changed ead62b3accb8
- 5d ago Changed ab01d7582411
- 7d ago Changed 621b6d2b20a2
- 9d ago Changed · +6 lines f32c9d928886
- 1mo ago First seen · 11 lines scan A 0d37c3528c18
pocketto is a plugin published in the GitHub repository rfxlamia/pocketto (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
code-craftsmanship
Code quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of Software Design (John Ousterhout), The Pragmatic Programmer (Hunt & Thomas), Domain-Driven Design (Eric Evans), Working Effectively with Legacy Code (Michael Feathers), and Google's…
aspark
An agile AI product team for Claude Code — Specify, Plan, Act, Review, Keep. A Product Owner, Designer, Engineering Manager, Reviewer, QA Tester and Release Manager work your feature through a gated delivery loop.
open-pr
Pre-flight checks and PR creation workflow: run tests, open a PR, code review, and check CI.
review
Code review for a branch, PR, or path — structured output with severity labels and cross-file analysis.
the-bulwark
Full-lifecycle SDLC guardrailing framework for Claude Code — from product ideation and planning through implementation, code review, and test validation. Enterprise-grade skills and agents for AI-human peer collaboration.
x-dev-pipeline
Structured dev workflow with spec, user-global risk RAG, task breakdown, execution, verify, qa-gate, fix loops, and audits.