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/vouchdev/vouch/vouch-recallgit clone --depth 1 https://github.com/vouchdev/vouchWhat 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 | $0.00011 | $0.00174 |
| Opus 5 | $0.00005 | $0.00087 |
| Sonnet 5 | $0.00002 | $0.00035 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
vouch-recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/vouch-recall
Use vouch's kb_context MCP tool to assemble a working set of claims, sources,
and entities the KB already has on the current topic. Print them with their
ids and citations; do not write anything.
Steps:
- Call
kb_contextwithquery: "$ARGUMENTS". - List every returned claim by id + one-line text; for each, show the source ids it cites.
- End with a one-sentence summary of what's missing from the KB on this
topic — the gap the user can fill with
/vouch-propose-from-prorkb_propose_claim.
Be terse. The KB is meant to remove ambiguity, not pad it.
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 · 21 lines · 11 tokens per session scan A f63116d172b8
vouch-recall is a command published in the GitHub repository vouchdev/vouch (91 stars, last pushed 10d ago), licensed MIT. It adds 11 tokens to every session and 174 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.
Other commands, from other repositories
spec-design
Create comprehensive technical design for a specification.
validate-gap
Analyze implementation gap between requirements and existing codebase.
spec-impl
Execute spec tasks using TDD methodology.
security-dialogs
Deep AI-based credential scan for dialog files.
security
Провести аудит безопасности кода.
gsd:list-phase-assumptions
Surface Claude's assumptions about a phase approach before planning.