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.
/plugin marketplace add pjt222/agent-almanacnpx agentmods add plugins/pjt222/agent-almanac/agent-almanacgit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/agent-almanac)<a href="https://agentmods.dev/plugins/pjt222/agent-almanac/agent-almanac"><img src="https://agentmods.dev/badge/plugins/pjt222/agent-almanac/agent-almanac.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agent-almanac 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 4d 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": "agent-almanac",
"description": "361 agentic skills across 65 domains, 72 agent personas, and 17 team compositions following the agentskills.io open standard",
"version": "1.0.0",
"author": {
"name": "Philipp Thoss",
"email": "[email protected]",
"url": "https://github.com/pjt222"
},
"repository": "https://github.com/pjt222/agent-almanac",
"homepage": "https://agentskills.io",
"license": "MIT",
"keywords": [
"skills",
"agents",
"teams",
"agentic",
"agentskills",
"devops",
"compliance",
"mlops",
"r-packages",
"esoteric"
]
}
What it installs
The manifest is a name and a version. 58 agents travel with it, and installing the plugin installs all of them — 1,797 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent designer A 29 tokens
- Agent apa-specialist A 34 tokens
- Agent artisan A 39 tokens
- Agent gardener A 29 tokens
- Agent ip-analyst A 19 tokens
- Agent librarian A 26 tokens
- Agent memex-keeper A 44 tokens
- Agent quarto-developer A 29 tokens
- Agent advocatus-diaboli A 38 tokens
- Agent blender-artist A 33 tokens
- Agent citizen-entomologist A 36 tokens
- Agent diffusion-specialist A 27 tokens
- Agent fabricator A 25 tokens
- Agent hildegard A 47 tokens
- Agent kabalist A 31 tokens
- Agent martial-artist A 29 tokens
- Agent mystic A 23 tokens
- Agent physicist A 31 tokens
- Agent polymath A 25 tokens
- Agent security-analyst A 19 tokens
- Agent acp-developer A 38 tokens
- Agent adaptic A 35 tokens
- Agent alchemist A 32 tokens
- Agent auditor A 35 tokens
- Agent chromatographer A 23 tokens
- Agent conservation-entomologist A 32 tokens
- Agent devops-engineer A 28 tokens
- Agent dog-trainer A 25 tokens
- Agent frontend-runtime-verifier A 46 tokens
- Agent geometrist A 30 tokens
- Agent gxp-validator A 53 tokens
- Agent hiking-guide A 29 tokens
- Agent janitor A 32 tokens
- Agent jigsawr-developer A 39 tokens
- Agent lapidary A 23 tokens
- Agent logician A 28 tokens
- Agent markovian A 28 tokens
- Agent mcp-developer A 27 tokens
- Agent mlops-engineer A 31 tokens
- Agent number-theorist A 27 tokens
- Agent prospector A 25 tokens
- Agent putior-integrator A 30 tokens
- Agent relocation-expert A 30 tokens
- Agent senior-data-scientist A 24 tokens
- Agent cli-developer A 29 tokens
- Agent code-reviewer A 24 tokens
- Agent contemplative A 31 tokens
- Agent edge-ai-engineer A 38 tokens
- Agent kernel-optimizer A 30 tokens
- Agent project-manager A 31 tokens
- Agent claw-polisher A 43 tokens
- Agent framework-scout A 31 tokens
- Agent your-agent-name A 17 tokens
- Agent nlp-specialist A 44 tokens
- Agent etymologist A 36 tokens
- Agent empirical-investigator A 32 tokens
- Agent mycologist B 27 tokens
- Agent r-developer B 21 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.
- 4d ago First seen · 26 lines scan A fb2a2b5fc34e
agent-almanac is a plugin published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
agentic-workflow
Stack-agnostic agent skills for a disciplined, doc-driven feature/issue workflow: design, plan, execute by phases, review, audit, and ship — with a full internal review pack and merge gates.
fw-publish
Publish Platform 3.0 custom apps to the Freshworks Marketplace using MCP tools (validate, pack, app-upload, submit/update).
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.