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/memorygit 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 | $0.00048 | $0.00855 |
| Opus 5 | $0.00024 | $0.00428 |
| Sonnet 5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/abcd:memory — curated knowledge substrate
The per-project compounding-curated knowledge substrate at .abcd/memory/.
Bare invocation performs zero writes.
Status (bare)
"${CLAUDE_PLUGIN_ROOT}/abcd" memory --json
Summarise the JSON: pages and by_class (page count per source class),
last_ingest, any contradictions, and per-source headroom lines. The bare
render never rebuilds or mutates the coverage index.
Ingest a source
Distil an external source (transcript / article / URL) into typed, cited memory pages. PDF is a later-phase seam: the binary rejects a PDF source with a clear error, because no text-extraction dependency is wired.
You are the distiller: read the source, produce the
DistilledPage JSON array, and pass it to the binary via --pages-json
(a file, or - for stdin). The binary computes the provenance, licence, and
content hash, validates every page, and writes atomically.
"${CLAUDE_PLUGIN_ROOT}/abcd" memory ingest <path-or-url> --pages-json distilled.json --json
Add --keep-original to retain the source at
.abcd/memory/sources/<sha256>.<ext> (the lifeboat licence gate — not launch —
governs its export). Report status, licence, and the written pages. An
already-known source re-ingests from the registry with no --pages-json.
Ask memory
Deterministic retrieval over the store, then a cited answer:
"${CLAUDE_PLUGIN_ROOT}/abcd" memory ask "<question>" --json
The default answer is the deterministic citation-renderer over the top-ranked
pages; every citation references source_class, citation, and source_hash.
--top-n sets the retrieval depth; 0 uses the pinned default. Optionally
file the answer back as a new page with --file-back --page-json <file|-> (one
DistilledPage object you produce from the retrieved matches).
Report the answer and, if present, the file_back result.
Lint
Full-store curator health-check — per-page quotation budgets, cumulative source coverage, source-class and licence advisories:
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 · 81 lines · 48 tokens per session scan A ca7b3e807e85
memory is a command published in the GitHub repository intentdriven/abcd (3 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 855 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.