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/ahoygit 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 | $0.00041 | $0.03174 |
| Opus 5 | $0.00020 | $0.01587 |
| Sonnet 5 | $0.00008 | $0.00635 |
| Haiku 4.5 | $0.00004 | $0.00317 |
Grade A, and why
ahoy 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:ahoy install/update detector
Run abcd's install/update engine for the current repo and present the result.
Bare invocation and the doctor, dry-run and remote sub-verbs perform zero
writes; install, uninstall and remote apply are the three that change
something, and each says so before it runs — remote apply is the only one that
changes state outside this machine, and it asks before it does.
Read $ARGUMENTS for the sub-verb. No argument, or status, is the bare
read-only detection pass below.
Bare — read-only detection
Run:
"${CLAUDE_PLUGIN_ROOT}/abcd" ahoy --json
Then summarise the JSON for the user:
folder_kind—managed-repo,unmanaged-repo, orunmanaged-folder.plugin_root_statusandroot_sha— where abcd is anchored.signals.install_mode— the PATH-entry install mode:dev (tip build)when the track-latest dogfood shim is installed,pinnedfor the abcd-owned copy of the verified release binary, empty when there is nothing onPATHyet. Either non-empty value may carry a trailing(shadowed on PATH)when anotherabcdcomes first onPATH. Report it so a dev install — or an entry abcd wrote that is not the one that runs — is never invisible.vintageandstaleness— 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. Report them so a binary running behind its own source is never silent. The comparison is disk-only — no network.banlist— the two-layer name guard, when the folder is a repo:hookandmerge_hook(installed/absent/foreign/unreadable), whether this clone is armed (hooks_path_armed),public_family, and the private layer's state on this machine (private_store, and its shape —private_keyed,private_entries,private_unparsed). Never report aforeignhook as abcd's guard, and never report a committed hook as a running one. Relayreachverbatim: it is the one sentence stating what the private layer does NOT cover, and a paraphrase drops the half that matters.gaps— how many are outstanding, and for each actionable one itstitle,category, andfix_hint; call out which arerequired.
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 · 250 lines · 41 tokens per session scan A 847d2b8e6f84
ahoy is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 3,174 once invoked, about $0.0002 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.