vouch-remember

A command that turns something the user says into proposed, cited information for the vouch knowledge base. The proposal remains hidden from searches until a human reviews and approves it.

In plain words
What is it for?
It helps record durable facts about people, organisations, and projects, including new entities and links between them. It reports the proposals that need review.
Why use it?
It preserves useful facts without allowing unverified statements to become trusted knowledge automatically.

Command for Claude Code

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/vouchdev/vouch/vouch-remember
Clone the repo
git clone --depth 1 https://github.com/vouchdev/vouch

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 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 $0.00014 $0.00232
Opus 5 $0.00007 $0.00116
Sonnet 5 $0.00003 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured 2d ago against content hash 534667af10ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vouch-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.

adapters/claude-code/.claude/commands/vouch-remember.md · 23 lines

What it actually says

/vouch-remember

Turn "$ARGUMENTS" into durable KB knowledge — proposed, never self-approved.

Steps:

  1. Call kb_register_source with the user's exact wording as content (source_type: "message", a short descriptive title). Sources are evidence intake; registering one writes no knowledge.
  2. Distill the durable fact(s) into one kb_propose_claim each, citing the registered source id in evidence. Keep each claim one sentence, present tense, self-contained.
  3. If the fact is about a person, org, or project the KB doesn't know yet, also file kb_propose_entity (and kb_propose_relation to link it).
  4. Report the proposal id(s) and remind the user: pending items are invisible to retrieval until a human runs vouch approve <id> or vouch review.

Never call kb_approve — the human at the gate decides what the KB believes.

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 · 23 lines · 14 tokens per session scan A 534667af10ca

Subscribe to this mod's changes

vouch-remember is a command published in the GitHub repository vouchdev/vouch (92 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 232 once invoked, about $0.0001 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.