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/zircote/subcog/recallgit clone --depth 1 https://github.com/zircote/subcogWhat 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 | $0.00714 |
| Opus 5 | $0.00005 | $0.00357 |
| Sonnet 5 | $0.00002 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/subcog:recall
Search the memory system for relevant decisions, learnings, patterns, and context.
Usage
/subcog:recall "database storage decision"
/subcog:recall --namespace decisions "storage"
/subcog:recall --mode vector "error handling patterns"
/subcog:recall --format md "API design patterns"
/subcog:recall --limit 5 "API design"
Arguments
Execution Strategy
Result Interpretation:
- Score 0.9+: Very high relevance (likely exact match)
- Score 0.7-0.9: Good relevance (closely related)
- Score 0.5-0.7: Moderate relevance (broader context)
- Score <0.5: Low relevance (may be tangential)
Search Tips
For patterns:
/subcog:recall --mode vector "resilient service patterns"
For debugging help:
/subcog:recall --namespace learnings "gotcha"
For exact terms:
/subcog:recall --mode text "PostgreSQL"
Examples
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 · 94 lines · 11 tokens per session scan A 15bedf9ca918
recall is a command published in the GitHub repository zircote/subcog (28 stars, last pushed 29d ago), licensed MIT. It adds 11 tokens to every session and 714 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
learn
교훈 기록 + 자동화 제안 (v6 - suggest-automation 통합).
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
tm-save
Save this session's durable memory to trailmem before you exit.
setup
kb MCP 연결 점검·재설정 안내 — 설치 직후 연결 확인, 서버 URL/토큰 변경, 연결 실패 진단에 사용.