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/versiongit 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 | $0.00029 | $0.00817 |
| Opus 5 | $0.00015 | $0.00409 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
version scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/abcd:version
Report the installed abcd version, install mode, and vintage — the running binary's build revision (in a source checkout) or pinned version, and whether it is up to date, stale, or of an undeterminable vintage relative to the on-disk reference. This command performs zero writes and touches no network.
Run:
"${CLAUDE_PLUGIN_ROOT}/abcd" version --json
Then tell the user the name, version, vintage, and staleness from the
JSON, plus install_mode when it is present — the key is omitted entirely when
no abcd-owned PATH entry is resolvable (nothing installed yet, a foreign or
dangling entry, or an unresolved plugin root). In that case say abcd is not on
PATH yet and point at ahoy install below, rather than inventing a mode.
Checking for a newer release. Only when the user explicitly asks whether a
newer version exists, add --check:
"${CLAUDE_PLUGIN_ROOT}/abcd" version --check --json
--check reaches the network — it fetches the latest release once, compares,
and reports under check (with its source named). abcd never fetches
implicitly (adr-38): the network is only ever touched by a verb whose documented
job is that fetch — version --check, update, docs cite refresh, and
memory ingest <url>; every other path reads only what is on disk.
Binary resolution. Run "${CLAUDE_PLUGIN_ROOT}/abcd" — a plugin install
provisions the binary into the plugin root, so this is the rung that fires for a
plugin user. If that path does not exist, try abcd on PATH; if that fails
too, you are in a source checkout of this repo, where — and only there —
go run ./cmd/abcd works, the published payload carrying no cmd/. To put a
binary on PATH, run ahoy install through whichever rung just resolved:
"${CLAUDE_PLUGIN_ROOT}/abcd" ahoy install, abcd ahoy install, or
go run ./cmd/abcd ahoy install in a source checkout.
When no binary resolves. If every rung fails, the fix is not to install Go. A compiler is a dependency of neither supported install route, which both provision a prebuilt, checksum-verified binary. Tell the user to recover in this order, no toolchain needed:
- Restart a session with network access.
hooks/bootstrap.shre-provisions the plugin-root binary at the start of every session that can reach the release origin; an empty.bootstrap.attemptmarker with no binary beside it means a previous provisioning began and did not finish, so a networked restart lands it. - Reinstall the plugin from its marketplace when its remote is stale (for example one predating an organisation rename). Re-adding the marketplace re-points it at the live release origin; the install guide gives the exact steps.
- Install the CLI binary with the one-liner in the README, which downloads and
SHA-256-verifies the same prebuilt binary into
~/.local/bin.
go run ./cmd/abcd and go build ./cmd/abcd serve only a source checkout of this
repo (contributors) or a platform carrying no released binary; they are never a
prerequisite for a plugin or CLI user.
User input: $ARGUMENTS
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 · 67 lines · 29 tokens per session scan A 2ff0a8f9ff05
version is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 817 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
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.