app-memory

A command for governing durable memory: agents can suggest notes, but a named reviewer must approve them before promotion. The record keeps history and source details for auditing.

In plain words
What is it for?
Use it to propose and review project or other scoped memories, recording their source, confidence, expiry, and links to superseded or conflicting entries.
Why use it?
Unreviewed memories can be wrong, out of scope, or conflict with newer information. The process preserves rejected and contradictory entries while making approval accountable.

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/vmobifystudio/app-dev-team/app-memory
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 156 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 $0.00000 $0.00156
Opus 5 $0.00000 $0.00078
Sonnet 5 $0.00000 $0.00031
Haiku 4.5 $0.00000 $0.00016

Measured yesterday against content hash ff08afce06f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-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/app-memory.md · 15 lines

What it actually says

/app-memory — govern durable memory

Agents may propose memory, but only a named reviewer can promote it:

node "${CLAUDE_PLUGIN_ROOT}/scripts/memory-curator.mjs" propose \
  --class project --content "..." --source docs/90-learnings.md \
  --scope project --confidence 0.8 --by <role>
node "${CLAUDE_PLUGIN_ROOT}/scripts/memory-curator.mjs" review \
  --id MEM-... --reason promote --content "why this is safe" --by <reviewer>

Every candidate carries provenance, scope, confidence, expiry, and supersession/contradiction links. The ledger is append-only; rejected or contradicted memories remain visible for audit.

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 · 15 lines · 0 tokens per session scan A ff08afce06f5

Subscribe to this mod's changes

app-memory is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 156 tokens. 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.