search-memory

search-memory is a skill for Claude Code, Codex from Glad-Labs/poindexter. It costs 54 tokens per session (404 once invoked), scanned A, original, Apache-2.0.

A tool for searching semantic memory: stored content such as notes, posts, issues, and audit records, matched by meaning rather than exact words.

In plain words
What is it for?
Use it to recall what is known about a topic and find related references from the connected memory store.
Why use it?
It helps find relevant earlier information when you do not remember the exact wording or location.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to recall what is known about a topic and find related references from the connected memory store.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glad-labs/poindexter/search-memory
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.

Any agent
npx skills add Glad-Labs/poindexter --skill search-memory
Clone the repo
git clone --depth 1 https://github.com/Glad-Labs/poindexter

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for search-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/glad-labs/poindexter/search-memory/github.svg)](https://agentmods.dev/skills/glad-labs/poindexter/search-memory)
Your own site
<a href="https://agentmods.dev/skills/glad-labs/poindexter/search-memory"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/search-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for search-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/glad-labs/poindexter/search-memory"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/search-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00404
Opus 5 $0.00027 $0.00202
Sonnet 5 $0.00011 $0.00081
Haiku 4.5 $0.00005 $0.00040

Measured 10d ago against content hash 2cd75b39310e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

search-memory 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/poindexter/search-memory/SKILL.md · 41 lines

What it actually says

Search Memory

Vector-search across the unified embeddings table (poindexter_brain.embeddings — ~25K rows spanning posts, memory files, issues, audit log, brain decisions, claude_sessions). Returns the top hits with similarity scores so the agent can decide how confidently to surface them.

Backed by the worker's /api/memory/search endpoint, which fronts MemoryClient.search (pgvector cosine similarity over nomic-embed-text:768 embeddings).

Usage

scripts/run.sh "<query>" [limit] [min_similarity]

Parameters

  • query (string, required): natural-language search query
  • limit (int, optional, default 5): top-N results to return
  • min_similarity (float, optional, default 0.5): drop hits below this threshold (0..1)

Output

Plain-text summary of hits, one per line, prefixed with [similarity] [source_table] source_id. Suitable for direct TTS readback in voice contexts.

Example

> scripts/run.sh "backup strategy" 3 0.5
Memory search: "backup strategy" (3 results)

1. [0.7821] [memory] feedback_backup_strategy
   Tier 1 in-stack hourly+daily, Tier 2 off-machine via restic...
2. [0.6547] [post] post_142
   Why solo founders need ruthless backup discipline...
3. [0.5912] [memory] project_disaster_recovery
   2026-05-05 incident: postgres-local volume wiped during Docker Desktop reinstall...
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 41 lines · 54 tokens per session scan A 2cd75b39310e

Subscribe to this mod's changes

search-memory is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 404 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

crawl4ai

AI-friendly web crawling and content extraction via Crawl4AI. Use when: (1) need to scrape web pages for AI consumption, (2) extract structured data from websites, (3) convert web content to clean Markdown, (4) build RAG knowledge bases from web sources. Preferred over basic fetch when pages have JS rendering or…

djblack1209-coder/OpenClaw-Bot · 75 tokens

feishu-wiki

Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.

djblack1209-coder/OpenClaw-Bot · 24 tokens

status

Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers. Trigger with /hyperflow:status, "what is hyperflow doing", "show task progress", "where are we".

jeremylongshore/tons-of-skills-marketplace · 72 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

notes

Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.

Pinvou/pinvou-agent · 0 tokens

exploiting-format-string-vulnerabilities

Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.

xalgorix/xalgorix · 69 tokens