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/intentdriven/abcd/launchgit clone --depth 1 https://github.com/intentdriven/abcdWhat 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 | $0.00085 | $0.04868 |
| Opus 5 | $0.00043 | $0.02434 |
| Sonnet 5 | $0.00017 | $0.00974 |
| Haiku 4.5 | $0.00009 | $0.00487 |
Grade A, and why
launch 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.
How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:launch release preview and release cut
Two flows over the abcd binary, kept apart on purpose:
- preview (
dry-run) — the bundle, the scan, and the gates. Zero writes. - ship — the release cut: derive the version from what shipped, compose the
changelog prose, write the dated heading. It writes one file,
CHANGELOG.md, and never publishes.
Neither flow publishes. Tagging is .github/workflows/auto-release.yml's job, and
it reads the dated heading ship writes.
Release day: what a human actually does
The rest of this page describes the verbs. This section describes the day — what you click, what runs on its own, and where it stops and waits for you. Read it if you are cutting a release and are not the person who built the machinery.
Nothing here publishes by accident. The release stops and asks for a human twice: once when you merge, and once at a deployment gate that no merge can bypass.
The shape of it
| # | Step | Who |
|---|---|---|
| 1 | Run the two semantic passes; record their receipts | you, with the agent |
| 2 | Prove the release gate locally | you, one command |
| 3 | Open the release PR, wait for green, merge | you, in GitHub |
| 4 | Tag the release | automatic |
| 5 | Build, checksum, attest, publish | stops and waits for your approval |
| 6 | Deploy the website from the tag | automatic, after step 5 |
| 7 | Update your plugin and check what you got | you, locally |
Steps 4-6 are one GitHub Actions run. You do not visit Cloudflare: the site deploy is invoked by the release workflow, so approving step 5 releases step 6 with it.
Step 3 — merging, and the one hazard
Merge the release PR the normal way, from the PR page's Merge pull request button (or the merge queue if the repository uses one).
Then let nothing else merge until the tag exists. This is the only part of release day with a trap in it. The release workflow works out which commit the reviewers actually read by walking back from the merge, so another PR landing in the gap makes it read the wrong commit, and the receipts you just recorded no longer match. The window is a minute or two. Tell anyone else working in the repository to hold.
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 · 391 lines · 85 tokens per session scan A fe6be4203ed2
launch is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 4,868 once invoked, about $0.0004 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
legal
Primary entry point for all BetterCallClaude requests — classifies intent, resolves jurisdiction (via swiss-legal-research), runs inline briefing for complexity 4–6, activates full briefing session when complexity ≥ 7 (via legal-intake skill), and routes to specialist agents or workflow pipelines. Invoked explicitly…
briefing
Structured pre-execution briefing session -- collects case context through specialist panel, builds execution plan, supports resume and depth control.
help
Show complete BetterCallClaude command reference, available agents, skills, and usage examples.
legal-5step
Execute the BetterCallClaude 5-step Swiss legal framework: intake → research → strategy → adversarial → draft. A complete end-to-end pipeline for any Swiss legal matter, from document analysis through final legal output.
legal-loop
Iterate a worker-evaluator cycle against a Goal Record until the success condition is met or a stop limit is reached. The evaluator (a different agent than the worker) judges each iteration using MCP verification tools. Produces an auditable verdict trail and a final MET / NOT MET status.
workflow
Define and execute multi-agent legal workflows -- due diligence, litigation prep, contract lifecycle, real estate closing.