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/documentgit 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 | $0.00020 | $0.00487 |
| Opus 5 | $0.00010 | $0.00244 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
document 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 yesterday.
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.
What it actually says
document
Bring the human-facing docs in line with what actually exists. Not a phase — a reconciler you run whenever code and docs have drifted. It detects drift; it does not re-interview the project.
Scope
- IN: README, ARCHITECTURE.md prose accuracy, curating docs/MEMORY.md.
- OUT: making product/architecture decisions (that's
/explore,/design). If reconciling reveals an undecided question, log it and point at the owning command — don't decide it here.
Preflight
- Read
CLAUDE.md,docs/PROJECT.md,docs/ARCHITECTURE.md,docs/SPEC.md,docs/MEMORY.md,README.md. - Read the actual code/structure. Diff docs vs. reality, not docs vs. docs. Build a short drift list (claimed but absent, present but undocumented, contradictions).
Interview
Minimal and targeted. Only ask when reconciliation is genuinely ambiguous (e.g. "ARCHITECTURE says Postgres, code uses SQLite — which is intended?"). No standing question bank. If nothing is ambiguous, ask nothing.
Produce
- README.md (owned): accurate for a human arriving cold — what it is, how to run it, how to test it, where the docs are. Concise.
- docs/ARCHITECTURE.md: correct stale prose to match reality. Don't
redesign — if reality diverged from a deliberate decision, flag it for
/designrather than rewriting the decision. - docs/MEMORY.md (curated here): dedupe, order by date, keep it a tight log of decisions-made-with-AI and why. This is the project's memory for Claude Code — terse, durable, not a changelog of everything.
Hand off
Report the drift found and what you reconciled vs. flagged. Suggested next is
context-dependent — e.g. /design if a contradiction needs a real decision,
otherwise nothing.
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.
- yesterday First seen · 50 lines · 20 tokens per session scan A 3f74c109dc7c
document is a command published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 487 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.