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/procoders/superpowers-v/v-memory-refreshgit clone --depth 1 https://github.com/procoders/superpowers-vWhat 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 | $0.00065 | $0.00445 |
| Opus 5 | $0.00032 | $0.00222 |
| Sonnet 5 | $0.00013 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
v-memory-refresh 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.
What it actually says
You are running /v:memory-refresh. Args: {{args}}.
Default — offline, FTS5, no install, no network:
python3 scripts/compound-v-memory.py refresh
python3 scripts/compound-v-memory.py doctor
Report the doctor summary (files / chunks / staleness / whether embeddings are bootstrapped).
Semantic lane (opt-in). Embeddings are OFF by default and live outside the repo
(~/.cache/compound-v/memory/<repo-id>/). Enabling them is the only step that touches
the network — and it must be explicit, never from a hook:
python3 scripts/compound-v-memory.py bootstrap # creates the out-of-repo venv + model (one time)
python3 scripts/compound-v-memory.py refresh --with-embeddings # populate vectors
If the project opted into embeddings at /v:init (memory.embeddings: true in
.claude/compound-v.json), the engine already adds vectors on a plain refresh once
bootstrapped — you don't need the flag. If {{args}} asks for --with-embeddings and
doctor shows embeddings are not bootstrapped, run bootstrap first (tell the user it will
download a ~200 MB model once).
The semantic lane is scale-gated: it only changes ranking once the corpus is large
enough to matter; on a small corpus FTS5 already wins. If bootstrap fails (offline / no
wheels), the engine stays FTS5-only — recall still works. See
skills/compound-v/memory.md.
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.
- 2d ago First seen · 34 lines · 65 tokens per session scan A bf8eeda21bb8
v-memory-refresh is a command published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 445 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 2026-08-30.
Other commands, from other repositories
index-management
Create, inspect, and drop search indexes. Wait for indexing to complete after data changes. Indexes automatically track Redis keys matching a specified prefix.
volume-stats-reset
Resets operation counters to zero for a named volume.
deepen
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
research
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.
review
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
session-end
Guided end-of-session ritual. Writes structured handoff (session-handoff.md), appends progress.md entry, and offers over-budget state archival + TOC refresh + git commit.