conjure-help

conjure-help is a command for coding agents from john-farina/claude-plugins. It costs 46 tokens per session (1,672 once invoked), scanned B, original, MIT.

A help command for Conjure, a toolkit that creates Claude Code extensions such as slash commands, agents, automatic event scripts, and connections to outside services.

In plain words
What is it for?
Use it to find the command for a specific extension, understand its syntax, and compare the available extension types.
Why use it?
It removes the guesswork of choosing the right Conjure command and shows the expected arguments and options.

Command

Part of the conjure plugin — 7 commands shipped together

Install

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.

agentmods
npx agentmods add commands/john-farina/claude-plugins/conjure-help
Clone the repo
git clone --depth 1 https://github.com/john-farina/claude-plugins

Or install conjure, the plugin that ships this one along with the rest of its 7 commands.

Wrote 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.

agentmods badge for conjure-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/john-farina/claude-plugins/conjure-help.svg)](https://agentmods.dev/commands/john-farina/claude-plugins/conjure-help)
Your own site
<a href="https://agentmods.dev/commands/john-farina/claude-plugins/conjure-help"><img src="https://agentmods.dev/badge/commands/john-farina/claude-plugins/conjure-help.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.01672
Opus 5 $0.00023 $0.00836
Sonnet 5 $0.00009 $0.00334
Haiku 4.5 $0.00005 $0.00167

Measured 3d ago against content hash 70a21fdda1fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

conjure-help scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Storage:** script at `~/.claude/hooks/<name>.sh` + entry in `~/.claude/settings.json`
plugins/conjure/commands/conjure-help.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conjure — Help

Conjure builds Claude Code extensions: skills (slash commands), agents (autonomous workers), hooks (event-driven scripts), and MCP servers (external connections). All commands support both create and update modes.


Which command do I use?

Does Claude need live access to an external system (DB, API, third-party service)?
  YES → /conjure-mcp

Should it fire automatically on an event (file edit, tool call, session start)?
  YES → /conjure-hook

Does Claude spawn it with its own context, model, or restricted tools?
  YES → /conjure-agent

Does the user type a /command to trigger it?
  YES → /conjure-skill

Not sure? → /conjure — auto-detects the type for you

Signal phrases:

You say… Use
"connect to", "integrate with", "query [DB/API]", "stop copy-pasting from [service]" /conjure-mcp
"whenever", "every time", "fires when", "on save", "after tool call", "session start" /conjure-hook
"investigate", "search in isolation", "spawn a worker", "orchestrate" /conjure-agent
"command", "slash command", "workflow I trigger", "checklist" /conjure-skill

Command Reference

/conjure — Unified entry point

Auto-detects type, runs intake, delegates to the right command.

/conjure                              Ask what you want to build
/conjure <description>                Auto-classify from description
/conjure help                         Show this help

/conjure-skill — Slash commands & workflows

/conjure-skill <name>                 Create (if new) or update (if exists)
/conjure-skill <name> faster          Speed-optimize: add ! pre-injection, strip prose
/conjure-skill <name> simpler         Reduce to 80% case, move edge cases to bottom
/conjure-skill <name> detailed        Expand: add phases, edge cases, examples
/conjure-skill <name> blank           Keep frontmatter, clear body
/conjure-skill <name> review          Quality gate: report issues + fix them
/conjure-skill <description>          Create with inline description — builds immediately

Read the full file on GitHub · 181 lines

Changes

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.

  1. 3d ago First seen · 181 lines · 46 tokens per session scan B 70a21fdda1fc

Subscribe to this mod's changes

conjure-help is a command published in the GitHub repository john-farina/claude-plugins (1 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,672 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other commands, from other repositories