memory

A per-project knowledge store in .abcd/memory/ for curated notes from sources such as transcripts, articles, and web pages.

In plain words
What is it for?
Use it to view the store, add distilled source notes, ask questions of the stored knowledge, or check its health.
Why use it?
It keeps reviewed project knowledge in one place and can report its coverage, contradictions, and source limits.

Command

Install

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.

agentmods
npx agentmods add commands/intentdriven/abcd/memory
Clone the repo
git clone --depth 1 https://github.com/intentdriven/abcd
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce 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

Measured yesterday against content hash ca7b3e807e85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/memory.md · 81 lines

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:

Read the full file on GitHub · 81 lines

Changes

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.

  1. yesterday First seen · 81 lines · 48 tokens per session scan A ca7b3e807e85

Subscribe to this mod's changes

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.

Related

Other commands, from other repositories