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/vldesigns/casebook/viewgit clone --depth 1 https://github.com/vldesigns/casebookWhat 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 | $0.00339 |
| Opus 5 | $0.00009 | $0.00169 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
view scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Give me a compact read of where .casebook/case-study.md stands — what's
filled in, what's still a placeholder, and what's waiting on my voice.
Read-only status pass — never edit the case study from this command.
Step 1: Preflight.
- If
.casebook/case-study.mddoesn't exist, suggest running/casebook:initand stop.
Step 2: Read the case study.
- Read
.casebook/case-study.mdin full.
Step 3: Report per canonical section — TL;DR, Context, The Problem, Process, Key Decisions, Outcomes, Reflections.
- For each: has real content, or is it still a placeholder stub (the
_(...)_italic convention from the template)? - Running Log: entry count, and the date of the newest entry.
- The list of OPEN
**› My take:**prompts, verbatim, across every section — this is my writing queue. Surface it as an invitation to fill them in, not a nag. - A total: sections/prompts filled vs. still open.
Step 4: Offer, don't auto-run.
- Mention
/casebook:exportfor a dated PDF (or HTML, if no browser is installed) snapshot of the case study, ready to share. (Equivalent to running"$CLAUDE_PLUGIN_ROOT/scripts/tracker" export --pdf --opendirectly.)
Output as a compact status report with simple section headings, not prose.
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 · 34 lines · 18 tokens per session scan A 28959b36c47c
view is a command published in the GitHub repository vldesigns/casebook (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 339 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
flux-generate
Generate epics and tasks in Flux from project requirements.
flux-add
Quickly add a task to Flux from a brief description.
card
Open one self-contained OverClick card.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
build-docs
Build and serve the docs site locally with Jekyll.
wisp-dashboard
Open the WISP dashboard in your browser.