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/john-farina/claude-pluginsWrote 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/john-farina/claude-plugins/conjure)<a href="https://agentmods.dev/plugins/john-farina/claude-plugins/conjure"><img src="https://agentmods.dev/badge/plugins/john-farina/claude-plugins/conjure/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/john-farina/claude-plugins/conjure"><img src="https://agentmods.dev/badge/plugins/john-farina/claude-plugins/conjure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
conjure 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 1mo 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": "conjure",
"version": "1.0.0",
"description": "Build Claude Code skills, agents, hooks, and MCP servers from plain-language descriptions. Generate, validate, and ship plugins without writing boilerplate.",
"author": {
"name": "John Farina",
"email": "[email protected]"
},
"keywords": [
"plugin-development",
"skill-generator",
"agent-builder",
"hook-builder",
"mcp-server-builder",
"scaffold",
"natural-language",
"plugin-creator",
"claude-code-plugin",
"extension-builder",
"skills",
"agents",
"hooks",
"mcp",
"developer-tools"
]
}
What it installs
The manifest is a name and a version. 7 commands travel with it, and installing the plugin installs all of them — 311 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 27 lines scan A e80cc2e6af7f
conjure is a plugin published in the GitHub repository john-farina/claude-plugins (1 stars, last pushed 5mo 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
mexican-mom
Mexican mom-inspired engineering discipline for coding agents.
fp-minify
Comment-concision mode. Shapes the code the model writes so comments earn their place (a non-obvious why, or meaning a name can't hold: config, units, constraints) and stay short. Hard one-line cap on inline comments, plus a density bar, so most functions carry none. Measurements, rejected alternatives, and the…
fp-sicem
Readable-prose mode. In the prose the model writes (READMEs, docs, markdown, PR and commit bodies) it defaults the em-dash out of existence, replacing it and its cousins (semicolon, colon-as-drama, long dash-parentheticals) with clear connectors that read well for every English reader, non-native ones included.…
fp-yoohoo
Terminal-recall mode. When Claude Code stops to ask you something (a permission prompt, a question dialog, an agent blocked on input) it brings the terminal window to the foreground, so a waiting session is impossible to miss and you never have to remember to check back. Skips the raise when the terminal already has…
fp-barbeque
Understanding-first mode: on exploratory tasks (refactors, design, ambiguous scope) the model grills you toward mutual understanding before it writes code, so you can debug and own the result. Sets a prior at the task edge; never steers mid-solve. Modes: off, on (default).
fp-honesty
Annotate load-bearing claims with their epistemic basis (verified/inferred/recalled/guess) and a per-response footer tally. Pure annotation — never changes what the model does.