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/atman-33/workhubWrote 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/atman-33/workhub/persona)<a href="https://agentmods.dev/plugins/atman-33/workhub/persona"><img src="https://agentmods.dev/badge/plugins/atman-33/workhub/persona/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/atman-33/workhub/persona"><img src="https://agentmods.dev/badge/plugins/atman-33/workhub/persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
persona 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 17d 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.
What it actually says
{
"name": "persona",
"version": "0.4.0",
"description": "Switchable response personas with a shared token-reduction engine: bundled characters (holmes, genshijin, noctis, lunafreya, ignis), user-defined characters that survive plugin updates, three compression levels persisted across sessions, a persona-switch CLI other skills can call, character-agnostic commit/review/compress/stats helpers, and an MCP description-shrinking proxy. Derived from genshijin (MIT).",
"author": {
"name": "atman-33",
"url": "https://github.com/atman-33"
}
}
What it installs
The manifest is a name and a version. 7 skills, 7 commands travel with it, and installing the plugin installs all of them — 470 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill persona-compress A 73 tokens
- Skill persona-help A 51 tokens
- Skill persona-commit A 54 tokens
- Skill persona-review A 47 tokens
- Skill persona-new A 52 tokens
- Skill persona A 55 tokens
- Skill persona-stats A 42 tokens
- Command persona A 13 tokens
- Command persona-commit A 12 tokens
- Command persona-compress A 18 tokens
- Command persona-new A 14 tokens
- Command persona-review A 11 tokens
- Command persona-stats A 14 tokens
- Command persona-help A 14 tokens
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.
- 17d ago Changed 9d1b2bf904fe
- 1mo ago Changed 46ded7d52112
- 1mo ago Changed 902d900ced2b
- 1mo ago Changed 49e0d8855b47
- 1mo ago First seen · 10 lines scan A dcae3743fe87
persona is a plugin published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), 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
superbrain
Automatic Claude Code -> Obsidian second brain: zero-config session capture, hybrid search, autonomous recall, daily/lessons/preferences.
ragkit
Standalone knowledge-base RAG (vector + lexical + metadata recall, RRF-fused).
skill-fetch
Search, discover, and install AI agent skills from 9 registries with quality scoring, security labels, and cross-platform support.
expo-launchpad
Idea-to-playable harness for Expo (React Native + TypeScript) apps and games: research, plan, design, contract, and a generator-evaluator build loop with skeptical QA. --kind app|game.
dding-dong
A Claude Code notification plugin that uses sounds and operating-system alerts when work finishes, fails, or needs input.
claude-bedrock
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills.