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/disembarkgit 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 | $0.00057 | $0.03219 |
| Opus 5 | $0.00028 | $0.01610 |
| Sonnet 5 | $0.00011 | $0.00644 |
| Haiku 4.5 | $0.00006 | $0.00322 |
Grade A, and why
disembark scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:disembark — pack a lifeboat
Mine a repository's record into a portable lifeboat at <dest>. The source is
never written — a probe and plan read it read-only, and the pack writes only
to the destination. This is the out-of-tree model (adr-35): point it at any repo,
touch nothing, write elsewhere.
Probe first (coverage readout)
See which brief sections a lifeboat could ground from the source, without writing anything. The repo argument is optional and defaults to the current directory:
"${CLAUDE_PLUGIN_ROOT}/abcd" disembark probe <source-repo> --json
This is the coverage experiment's read-only readout: every brief section comes
back marked grounded, partial, or blank, alongside what was searched. It
writes nothing into the source and runs in a small fraction of a full pack's time
(no delegated model work). coverage.{json,md} are written only by pack.
Dry run next (recommended)
Show the exact file set a pack would write, without writing anything:
"${CLAUDE_PLUGIN_ROOT}/abcd" disembark plan <source-repo> --json
Report file_count, total_bytes, manifest_sha256, and any omissions (records
too large or unreadable to carry). Then pack for real.
Scope: what the scan reads
The free-text tree scan — the one that grounds evidence and open-question
markers by reading source files — honours .gitignore by default. A file the
user told git to ignore is out of that scan, because a lifeboat cites its
evidence by path:line and is meant to be shared, so a scan that read ignored
files could carry a repository's scratch, logs and local notes into the
artefact. Declared record families (ADRs, issues, intents, specs) are a
separate path: pack copies them verbatim from their canonical locations
whether or not git ignores them, so a gitignored record still travels — keep a
record you do not want shared out of those locations, not merely in
.gitignore.
The salvage case is the other way round, and it is the case disembark exists
for: a dead or archived repository whose uncommitted residue is often the
most valuable thing left. Reach that with an explicit flag on any of the three:
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 · 246 lines · 57 tokens per session scan A 2439355b30cd
disembark is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 3,219 once invoked, about $0.0003 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.