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/robconery/cassini-workshop/initgit clone --depth 1 https://github.com/robconery/cassini-workshopWhat 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 | $0.00018 | $0.00731 |
| Opus 5 | $0.00009 | $0.00365 |
| Sonnet 5 | $0.00004 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
init 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init
Stand up the working files for a project so the later phase commands have something to fill. You create structure, not content — stubs with headings and TODOs, never invented decisions.
CLAUDE.md Template
Use this when creating CLAUDE.md
# [Fill in]
[Project summary, ask if there isn't one]
## Rules
- DO NOT REPORT SOMETHING IS FIXED IF YOU HAVEN'T COMPILED THE APP
- DO NOT SEARCH node_modules for answers. GO ONLINE.
- Use emoji for markdown documents for readability.
- Get to the point, be terse, do not over explain. Tokens are water, we're in the desert. Use emoji instead of prose if you can.
- Never install a package by editing the manifest, always use a package install tool, such as `npm install`, `bun install`, etc.
Scope
- IN: create CLAUDE.md, the
docs/skeleton, a README stub,.gitignore. - OUT: deciding what the project is (that is
/explore), architecture (/design), tasks (/plan). This command does not interview the problem.
Preflight
- Re-entrant: if a file already exists, leave it alone. Report what was already there vs. what you created. Never clobber.
- Detect the ground:
- Code already present → seed CLAUDE.md from what's actually there (language, test command, run command, layout). Be factual, no guessing.
- Empty dir → CLAUDE.md gets a stub with those headings and
TODO.
Produce
- CLAUDE.md (root, owned here) — the how: stack, conventions, test &
run commands, the phase commands available (
/explore,/design,/plan,/document), and the rule that each doc has one owner. - docs/PROJECT.md — stub, owned by
/explore. Headings: Problem, Who it's for, Goals, Scope (in/out), Open questions. - docs/ARCHITECTURE.md — stub, owned by
/design. - docs/SPEC.md — stub, owned by
/design. - docs/STORIES.md — stub, owned by
/plan. - docs/PLAN.md — stub, owned by
/plan. Empty checklist. - docs/MEMORY.md — the project decision log: decisions made with AI,
preserved for Claude Code. Header + an empty dated-entry list. Curated by
/document; appended to by every phase command. Distinct from the~/.claudememory system. - README.md — one-line stub, owned by
/document.
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.
- 2d ago First seen · 76 lines · 18 tokens per session scan A 13c609e53942
init is a command published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 731 once invoked, about $0.0001 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
git-remote
Create the GitHub remote for this project and make it look sharp — name, license, real README, contributing, security, issue templates.
git-merge
Merge the current branch into main safely — commit-check, remote sync, confirm, merge.
git-commit
Stage and commit current changes using Conventional Commits, branch-or-trunk by size. Uses the github skill.
init
Scaffold the project files I like — CLAUDE.md and the /docs skeleton.
git-pr
Open a pull request with a clear summary, verification plan, and risk note via gh pr create. Uses the github skill.
git-issue
Open a GitHub issue with a clear, detailed body via gh issue create. Uses the github skill.