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/capturegit 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 | $0.00044 | $0.01956 |
| Opus 5 | $0.00022 | $0.00978 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
capture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:capture — issue ledger
The lightweight write side of the structured issue ledger under
.abcd/work/issues/. Every issue gets a stable iss-N id, schema-checked
frontmatter, and folder-as-status (open/, resolved/, wontfix/). Bare
invocation performs zero writes.
Status (bare)
To render recent captures and counts:
"${CLAUDE_PLUGIN_ROOT}/abcd" capture --json
Summarise the JSON for the user: open_count / resolved_count /
wontfix_count, and for each entry in recent_open its id, severity, and
slug. No iss-*.md file is created, moved, or mutated by this invocation.
Which ledger? A half-formed observation, question, or nitpick goes to
/abcd:capture "…"; a user-facing change you want to ship goes to
/abcd:intent "…". For a big, unproven idea there is an optional third route:
/abcd:ideate runs the admission gauntlet and records the verdict either way.
It is a pointer, never a precondition — capture friction stays at one line.
Capture an issue
Append a structured issue from free-form text:
"${CLAUDE_PLUGIN_ROOT}/abcd" capture "<text>" --json
Provide provenance and taxonomy through flags when known (each falls back to a
default): --severity (nitpick|minor|major|critical, default minor),
--category (default observation), --source (default user-observation),
--found-during (session/command context, default manual-capture),
--found-at (optional repo-relative path), --slug (overrides the slug derived
from the text), --blocked-by (comma-separated iss-N ids this issue depends
on). Report the new id, status, and path from the JSON. Report redacted
too whenever it is non-zero: it counts the spans rewritten before the text was
written, and the user needs to know their wording was changed.
A single whitespace-free word is refused (exit 2, nothing written): a lone token reads as a mistyped sub-verb, never as issue text. A near-miss of a real sub-verb is refused the same way, with the correction named, so a two-word input containing a space is not automatically safe.
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 · 152 lines · 44 tokens per session scan A 1785172dd7d9
capture is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,956 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.