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 skills/kitchen-engineer42/joharnessburg/using-johnnpx skills add kitchen-engineer42/joharnessburg --skill using-johngit clone --depth 1 https://github.com/kitchen-engineer42/joharnessburgWrote 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/skills/kitchen-engineer42/joharnessburg/using-john)<a href="https://agentmods.dev/skills/kitchen-engineer42/joharnessburg/using-john"><img src="https://agentmods.dev/badge/skills/kitchen-engineer42/joharnessburg/using-john.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 | $0.00124 | $0.01926 |
| Opus 5 | $0.00062 | $0.00963 |
| Sonnet 5 | $0.00025 | $0.00385 |
| Haiku 4.5 | $0.00012 | $0.00193 |
Grade A, and why
using-john 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-john
You are running in a Claude Code or Codex session where the joharnessburg plugin is loaded. The user has installed John because they want you to do knowledge-dense app building — take unstructured input (a book, a regulation, a doc set, mixed media) and produce a working app whose every feature traces back to extracted knowledge. John is a harness; you are the agent it harnesses.
This skill is your orientation. Read it once at the start of any John session, and re-read after each context compaction.
What John actually is
A thin layer of skills, hooks, and a small toolkit on top of Claude Code or Codex. It does not replace your reasoning; it shapes how you organize the work so a knowledge-heavy project doesn't fall apart.
The shape John imposes is a two-axis matrix:
- Horizontal axis (phases): the work moves left-to-right through a small number of phases, one at a time. The knowledge phases (knowledge engineering) on the left half; the app phases (app building) on the right. You advance one phase before starting the next.
- Vertical axis (parallel knowledge entries): within most phases there are many similar units of work — hundreds of chunks to extract, dozens of skills to author, etc. You fan these out to subagents in parallel, not handle them serially in your own context.
Older projects and team shorthand may call the two halves by their legacy nicknames 2skills and 2app — same things. Same session, same memory, one PLAN.md spanning both halves.
Produced apps run standalone by default — locally or on any host the user owns, configured through .env, with no external auth/billing/telemetry platform assumed. Templates may add platform integration; vanilla John never requires it.
The user's working state — where to look
Everything John writes lives in the user's project directory (the current working directory when this session was started). You write here, not into John's plugin install location.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 80 lines · 124 tokens per session scan A 7764882157bc
using-john is a skill published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 1,926 once invoked, about $0.0006 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 skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
pm-verify-release-v1
Post-release acceptance verification, grade a shipped release against the spec that promised it. Use when someone says "verify the release", "did the release meet its acceptance scenarios", "post-release verification", "execute the measurement plan", "week-one metrics check", or hands a shipped scope that needs…