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.
npx agentmods add commands/john-farina/claude-plugins/conjure-configgit 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/commands/john-farina/claude-plugins/conjure-config)<a href="https://agentmods.dev/commands/john-farina/claude-plugins/conjure-config"><img src="https://agentmods.dev/badge/commands/john-farina/claude-plugins/conjure-config.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01397 |
| Opus 5 | $0.00018 | $0.00698 |
| Sonnet 5 | $0.00007 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00140 |
Grade A, and why
conjure-config 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/conjure-config — Manage Conjure Preferences
Conjure reads preferences from two optional plain-text files. Neither is required — conjure works without them.
- User-global:
~/.claude/conjure-config.md— applies across all projects - Project-local:
.claude/conjure-config.mdin the current working directory — supplements or overrides global for this project
Both are just markdown files with sections of natural-language instructions. Conjure commands read them at startup and follow whatever is written there. You can say anything — output paths, naming rules, required tools, code style constraints, workflow steps, template content. If Claude can understand it, conjure will follow it.
Phase 0: Parse Arguments
| Args | Action |
|---|---|
| (empty) | Interactive intake — ask what they want to configure |
show |
Print the current config (both files, labeled) |
remove <type> |
Remove a specific section (skills, agents, hooks, mcp, global) |
reset |
Clear a config file (confirm scope and confirm deletion) |
| Any other text | Treat as a description of the desired preference — go to Phase 2 |
Phase 1: Show Current Config (if show)
Read both config files and print them formatted:
~/.claude/conjure-config.md (global)
─────────────────────────────────────
[contents or "(empty)"]
.claude/conjure-config.md (project-local)
─────────────────────────────────────────
[contents or "(not found)"]
Done. No further phases needed.
Phase 2: Interactive Intake
If the user gave a description in $ARGUMENTS, use it as starting context. If they gave nothing, ask:
"What do you want conjure to do differently? Describe it however you like — a folder path, a naming rule, a code style requirement, a template, anything."
Then ask targeted follow-up questions via AskUserQuestion to get clarity. Use your judgment about what's ambiguous — not every answer needs follow-up. Common gaps to probe:
- Scope: does this apply to all conjure commands, or just one type (skills / agents / hooks / mcp)?
- Always vs. default: should this always happen, or only when no other instruction applies?
- Path ambiguity: if they gave a relative path, confirm the absolute path
- Condition: does this apply in all situations, or only when a condition is met?
- Conflicts: if this contradicts something already in the config, ask which wins
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.
- 5d ago First seen · 169 lines · 36 tokens per session scan A ad72c0d9baa9
conjure-config is a command published in the GitHub repository john-farina/claude-plugins (1 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,397 once invoked, about $0.0002 per session on Opus 5. 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 commands, from other repositories
karpenter
Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upgrade Karpenter v1.x on EKS. Covers NodePool, EC2NodeClass, NodeClaim, Spot diversity, disruption strategy, Pod Identity/IRSA, interruption queue, private clusters, AMI rotation, and GitOps integration. Use…
kingfisher
Find, live-validate, map the blast radius of, and revoke leaked secrets with Kingfisher (MongoDB) — across a local repo, Git history, a GitHub/GitLab/Bitbucket org, S3/GCS, Docker images, Slack, Jira, Confluence, Teams, or Postman. Covers local CLI scanning, direct validate/revoke without a scan, baseline management…
renovate
Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.
zizmor
Audit GitHub Actions workflows, composite actions, Dependabot configs, and pre-commit configs for security findings using zizmor — template injection, credential persistence, unpinned uses, over-broad permissions, impostor commits. Covers local CLI, auto-fix, zizmor.yml policy, severity-based CI gates, SARIF upload…
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
gitops
Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised…