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 skills add 23blocks-OS/ai-maestro-plugins --skill memory-searchgit clone --depth 1 https://github.com/23blocks-OS/ai-maestro-pluginsWrote 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/23blocks-os/ai-maestro-plugins/memory-search)<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/memory-search"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/memory-search.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 24 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 149 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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 5.1 | $0.00090 | $0.01332 |
| Opus 5 | $0.00045 | $0.00666 |
| Sonnet 5 | $0.00018 | $0.00266 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
memory-search 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Maestro Memory Search
CRITICAL: AUTOMATIC BEHAVIOR - READ THIS FIRST
THIS IS NOT OPTIONAL. THIS IS YOUR DEFAULT BEHAVIOR.
When the user gives you ANY instruction, you MUST FIRST search your memory for:
- Previous discussions - Have we talked about this before?
- Past decisions - What did we decide last time?
- Prior context - What does the user expect based on history?
- Earlier work - Did we already start on this?
DO NOT:
- Start fresh without checking conversation history
- Assume this is a new topic without verifying
- Skip memory search because "I don't remember discussing this"
- Wait for the user to say "remember when we..."
ALWAYS:
- Search memory IMMEDIATELY when you receive a task
- Search for terms and concepts the user mentions
- Check for previous decisions on similar topics
- Look for context that informs current work
The Rule: Receive Instruction → Search Memory → Then Proceed
1. User asks you to do something
2. IMMEDIATELY search memory for relevant context
3. NOW you know what was discussed before
4. NOW you can build on previous work, not start over
Available Commands
| Command | Description |
|---|---|
memory-search.sh "<query>" |
Hybrid search (recommended) |
memory-search.sh "<query>" --mode semantic |
Find conceptually related |
memory-search.sh "<query>" --mode term |
Exact term matching |
memory-search.sh "<query>" --role user |
Only user messages |
memory-search.sh "<query>" --role assistant |
Only your responses |
What to Search Based on User Instruction
| User Says | IMMEDIATELY Search |
|---|---|
| "Continue working on X" | memory-search.sh "X" |
| "Fix the issue we discussed" | memory-search.sh "issue", memory-search.sh "bug" |
| "Use the approach we agreed on" | memory-search.sh "approach", memory-search.sh "decision" |
| "Like we did before" | memory-search.sh "<topic> implementation" |
| Any specific feature/component | memory-search.sh "<feature>" |
| References to past work | memory-search.sh "<reference>" --mode semantic |
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.
- 8d ago First seen · 160 lines · 90 tokens per session scan A 44b6638d6fe2
memory-search is a skill published in the GitHub repository 23blocks-OS/ai-maestro-plugins (9 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,332 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
memory-search
Use this skill only when the user explicitly asks to query the EvoFlux application database with SQL for structured analysis that ordinary recall cannot answer: aggregating tool failures across sessions, filtering by role, agent, or time range, reconstructing a complete execution chain, or checking a remembered claim…
learner
Post-debugging knowledge extraction — captures non-obvious, codebase-specific learnings that pass quality gates. Invoke after resolving tricky bugs or discovering surprising behavior.
context-management
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage…
knowledge-persistence
Patterns for learning from corrections, capturing instincts, extracting stable patterns, and building cross-session knowledge. Use when the user corrects you, when you discover a recurring pattern, or when insights should persist beyond the current session.
memory-patterns
Patterns for structuring MEMORY.md and topic-based memory files for Claude Code persistent memory. Use when the user asks about remembering things across sessions, wants to organize project knowledge, or needs guidance on what to save vs not save.
context-engineering
Use this skill for optimizing AI context windows. Covers context sizing, prioritization, and avoiding context overflow.