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/packagingnpx skills add kitchen-engineer42/joharnessburg --skill packaginggit 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/packaging)<a href="https://agentmods.dev/skills/kitchen-engineer42/joharnessburg/packaging"><img src="https://agentmods.dev/badge/skills/kitchen-engineer42/joharnessburg/packaging.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 | $0.00137 | $0.02125 |
| Opus 5 | $0.00068 | $0.01063 |
| Sonnet 5 | $0.00027 | $0.00425 |
| Haiku 4.5 | $0.00014 | $0.00213 |
Grade A, and why
packaging 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
packaging
The knowledge phases end here. Packaging turns John's working knowledge state (in <project>/.john/knowledge/) into the deliverable that the app phases consume. For dual-provider projects, emit the same produced skills into both provider discovery roots:
- Claude Code:
<project>/.claude/skills/ - Codex:
<project>/.agents/skills/
After this phase, the produced skills are project-scoped skills auto-discovered by the matching provider session that builds the app.
Where the work happens
- Inputs:
<project>/.john/knowledge/<entry-id>/{header.md, body.md}(from [[knowledge-rewrite]]) - Outputs:
<project>/.claude/skills/<skill-name>/SKILL.md<project>/.agents/skills/<skill-name>/SKILL.md- optional
references/,scripts/,assets/in both provider roots when needed
<project>/.claude/skills/ is Claude Code's project-scoped skill auto-discovery path. <project>/.agents/skills/ is Codex's project-scoped skill auto-discovery path. Keep the two trees content-identical unless a provider-specific path or command truly requires a fork.
What "skill" means here
A skill in Claude Code is one directory with at minimum a SKILL.md:
<project>/.claude/skills/<skill-name>/ # Claude Code
<project>/.agents/skills/<skill-name>/ # Codex
├── SKILL.md # required: YAML frontmatter + markdown body
├── references/ # optional: deeper material loaded on demand
├── scripts/ # optional: executable code
└── assets/ # optional: templates, icons, fonts, etc.
The frontmatter has name and description. Optionally metadata.triggers[] for keyword-based auto-load. Body is markdown — what the agent should do/know.
This is the same skill format John itself ships. Your packaging output is structurally identical to a John meta-skill or phase skill — the difference is who wrote it (humans for John core; a John-equipped agent during the knowledge phases for produced knowledge).
Mapping knowledge entries → skills
What ships with it
3 files 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 · 127 lines · 137 tokens per session scan A c98b8e259478
packaging is a skill published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 2,125 once invoked, about $0.0007 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…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
ops-pocket
OPS on-demand: This skill should be used when the user asks to "pocket memos", "voice memo pipeline"…
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.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
codex-test-gen
Generate unit tests for specified functions using Codex exec.