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 skills/zircote/subcog/memory-recallnpx skills add zircote/subcog --skill memory-recallgit clone --depth 1 https://github.com/zircote/subcogWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zircote/subcog/memory-recall)<a href="https://agentmods.dev/skills/zircote/subcog/memory-recall"><img src="https://agentmods.dev/badge/skills/zircote/subcog/memory-recall.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00857 |
| Opus 5 | $0.00000 | $0.00428 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
memory-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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Recall Skill
Search and surface relevant memories to inform current work with decisions, patterns, and learnings from past sessions.
Trigger Phrases
- "what did we decide about", "how do we handle"
- "find memories about", "search for", "recall"
- "what's our approach to", "what patterns do we use"
- "any gotchas with", "lessons learned about"
- "previous decisions on", "remind me"
Quick Reference
| Search Mode | Best For | Example |
|---|---|---|
hybrid (default) |
General queries, balanced results | "database storage decision" |
vector |
Conceptual similarity, fuzzy matching | "how to handle errors gracefully" |
text |
Exact terms, specific keywords | "PostgreSQL" |
Execution Strategy
Search Quality Guidelines:
- Start broad, then narrow with namespace filters
- Use
vectormode for conceptual searches - Use
textmode when you know exact terms hybridmode (default) works best for most queries
Intelligent Search Workflow
- Understand the intent - what does the user need to know?
- Identify keywords - extract searchable terms
- Choose search mode based on query type
- Apply namespace filter if domain is clear
- Execute search via MCP tool or CLI
- Interpret results - explain relevance scores
- Synthesize findings - summarize key insights
Score Interpretation
Search Strategies by Use Case
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.
- 4d ago First seen · 108 lines · 0 tokens per session scan A 83015572f8aa
memory-recall is a skill published in the GitHub repository zircote/subcog (28 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 857 tokens. 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 skills, from other repositories
clawmem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring, and memory lifecycle (pin/snooze/forget). Use when tuning retrieval, troubleshooting recall quality, or any ClawMem…
engrama-onboard
Build a personalized Engrama memory graph for any user through a conversational interview. Use this skill whenever someone says "set up Engrama", "create my graph", "onboard", "build my profile", "configure Engrama for me", or asks how to start using Engrama. Also use when the user mentions they have a different role…
ariadne
Mandatory long-term memory workflow for Codex, Claude Code, and MCP clients backed by the local Ariadne server (Qdrant + bge-m3). Always use at the start or resumption of substantive project work, after context compaction, when prior work or decisions may matter, and immediately after durable decisions, gotchas…
check-memory-before-acting
Search this project's own memory before doing something it may already have opinions about. Use before running a build/test/deploy command, before choosing a library or approach, before changing configuration or CI, and before re-opening a decision that may already have been settled. Also use when a task resembles…
keep-memory-current
Load this project's memory when you start, and write back what you learned before you stop. Use at the beginning of a work session, when finishing a task or about to end a session, after debugging something non-obvious, after a decision that took argument to reach, and whenever you catch yourself thinking "I should…
kb-log
결정·삽질 즉시 기록 — 아키텍처/기술 결정을 내렸거나 버그의 원인을 규명한 "직후" 팀 지식베이스에 기록한다(recorddecision/recordlearning). kb MCP를 못 쓰는 상황(미연결, 서브에이전트)이면 .kb/ledger.jsonl 원장에 append해 유실을 막는다. "이 결정 기록해줘", "방금 삽질 남겨" 요청 시, 또는 중요한 결정·디버깅 완료 직후 자발적으로 사용.