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/ideategit 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 | $0.00050 | $0.01871 |
| Opus 5 | $0.00025 | $0.00936 |
| Sonnet 5 | $0.00010 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
ideate 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:ideate — the idea-admission gauntlet
An exciting idea is cheapest to kill in its first hour and most expensive to kill after it has minted intents, specs, and branches. This runs the admission interview and records the outcome.
Ideate is optional and never a gate. Nothing requires it: /abcd:capture and
/abcd:intent work exactly as they always do, and skipping ideate is not a
mistake to warn about. Reach for it when an idea is big and unproven enough that
being wrong about it would be expensive.
The binary does no judging. The three legs below are yours to run. abcd ideate record validates what they produced, proves every citation names a real
record, and writes the durable verdict. It never fetches a source and never
forms an opinion.
The three legs, in order
The order is not cosmetic — each leg changes what the next one is looking at —
and abcd ideate record refuses a payload whose legs are missing or out of
order.
Leg 1 — Primary-source research
Research the idea's load-bearing claims: the ones that, if false, take the idea with them. For each, open the primary source — the paper, the specification, the API reference, the original data — and check the claim against it.
A secondary citation is not a check. In the run this protocol comes from, three secondary-source claims were falsified once the primary was opened, one of them an extraction artefact that no source ever said.
Produce, for each claim: the claim, the primary source (a URL or a document
reference), and the finding — verified, falsified, or unverifiable. An
honest unverifiable is a result; a missing source is not, and the binary
refuses a claim that names none.
Leg 2 — Record grill
Read the existing record before anything else is decided — the brief, the
intents in every bucket (drafts/, planned/, shipped/, disciplines/,
superseded/), the ADRs, the principles, the research notes under
.abcd/development/research/notes/, and the decision log
.abcd/work/DECISIONS.md. Answer one question: does an entry already
cover, contradict, or supersede this idea?
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 · 162 lines · 50 tokens per session scan A f441e72d2675
ideate is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,871 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.