v-remember

A command that searches saved project notes for relevant past decisions, failures, plans, and routing lessons using V-memory.

In plain words
What is it for?
Finding related documents before planning or reviewing work, refreshing the search index when it is missing, and checking repeated file-pattern failures.
Why use it?
It gives planning and review work access to earlier evidence, while keeping routing decisions under the project's separate rules.

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/procoders/superpowers-v/v-remember
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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 $0.00079 $0.00356
Opus 5 $0.00039 $0.00178
Sonnet 5 $0.00016 $0.00071
Haiku 4.5 $0.00008 $0.00036

Measured 2d ago against content hash 3777f3f1cd45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

v-remember 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 2d ago.

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/v-remember.md · 25 lines

What it actually says

You are running /v:remember — V-memory recall. The query is {{args}}.

Run the recall and present what comes back:

python3 scripts/compound-v-memory.py search "{{args}}" --top 8

If it reports the index is missing, run /v:memory-refresh first, then retry.

Memory is EVIDENCE, not authority:

  • It surfaces related prior prose (specs, plans, reviews, archaeology, recon, routing lessons). It never decides routing — backend/model/isolation stay governed by routing-lessons.md + the scorecard, per routing-policy.md. Treat a retrieved chunk as a pointer to read, not a ruling.

  • When you need a structured "has this file pattern repeatedly failed before?" verdict that may auto-tighten the next run (force worktree / add a review pass / fold into Task 0), use the deterministic bridge instead:

    python3 scripts/compound-v-memory.py recall-check --files <glob> [<glob>…]
    

Authority doc: skills/compound-v/memory.md.

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. 2d ago First seen · 25 lines · 79 tokens per session scan A 3777f3f1cd45

Subscribe to this mod's changes

v-remember is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 356 once invoked, about $0.0004 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 2026-08-30.