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/docsgit 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 | $0.00063 | $0.01183 |
| Opus 5 | $0.00032 | $0.00592 |
| Sonnet 5 | $0.00013 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:docs documentation currency and citations
Two jobs live here. lint grades the documentation and writes nothing. cite
maintains the committed citation baseline that the lint then enforces offline.
lint — the currency gate (zero writes, zero network)
Run:
"${CLAUDE_PLUGIN_ROOT}/abcd" docs lint --json
Then summarise the JSON for the user:
blockers— how many blocker findings exist; any blocker fails the gate.findings— for each, itsFile,Line,RuleID,Severity, andMessage; group them so the user sees what to fix.
The lint enforces present-tense docs: unambiguous change-narration (previously,
formerly, renamed from, has been replaced, we switched, to be implemented) blocks, while phrases that also describe present state
(deprecated, no longer, migrated from) warn advisorily rather than block.
It also checks that relative links resolve and that no stray markdown sits at the
repo root (it belongs under docs/). Point the user at the offending file and
line for each finding, and note whether it is a blocker or a warning.
Where a repo arms them, the citation rules add: footnote markers and definitions in bijection, every crosswalk table row carrying a footnote, well-formed URLs and DOIs, refused source domains, and the committed baseline — no cited URL without a receipt, none recorded broken, none whose recorded final address has drifted from what the page cites, and a staleness warning past 180 days. Every one of these reads committed files only; nothing dials out.
--release-gate runs the same lint with one difference: a citation past the
365-day threshold blocks instead of warning. It is for release machinery only —
an ordinary commit is never blocked by the calendar.
If blockers is zero the docs are currency-clean.
cite refresh — the one verb that reaches the network
Run:
"${CLAUDE_PLUGIN_ROOT}/abcd" docs cite refresh --json
This fetches every cited URL once, bounded and without retries, and rewrites the baseline. Report from the JSON:
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 · 114 lines · 63 tokens per session scan A bd4f174c829e
docs is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,183 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.