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/softspark/ai-toolkit/mem-searchnpx skills add softspark/ai-toolkit --skill mem-searchgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/mem-search)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/mem-search"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/mem-search.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 | $0.00023 | $0.00581 |
| Opus 5 | $0.00012 | $0.00291 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
mem-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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Session Memory
Search the persistent memory database for past coding observations, decisions, and context.
$ARGUMENTS
How It Works
This skill queries the SQLite FTS5 full-text search index at ~/.softspark/ai-toolkit/memory.db to find relevant observations from past sessions.
Instructions
-
Parse the search query from
$ARGUMENTS. If empty, prompt the user for a query. -
Initialize the database if it does not exist:
python3 "$HOME/.softspark/ai-toolkit/hooks/../plugins/memory-pack/scripts/init_db.py" 2>/dev/null || true -
Run the FTS5 search against the observations table:
sqlite3 ~/.softspark/ai-toolkit/memory.db " SELECT o.id, o.session_id, o.tool_name, o.content, o.created_at, s.project_dir, s.summary FROM observations_fts fts JOIN observations o ON o.id = fts.rowid LEFT JOIN sessions s ON s.session_id = o.session_id WHERE observations_fts MATCH '<query>' ORDER BY rank LIMIT 10; "Replace
<query>with the user's search terms. Escape single quotes by doubling them. -
Progressive disclosure -- present results in two stages:
Stage 1: Summary view (show first)
## Memory Search: "<query>" Found N results across M sessions. | # | Session | Project | Tool | Time | Preview | |---|---------|---------|------|------|---------| | 1 | abc123 | /path | Edit | 2025-01-15 | First 80 chars... |Stage 2: Detail view (on request) Show the full observation content, session summary, and related observations from the same session.
-
If no results found, suggest:
- Trying broader search terms
- Checking if memory-pack hooks are installed
- Running
init-db.shif the database is missing
Query Tips
- Use simple keywords:
mem-search database migration - FTS5 supports prefix matching:
migrat*matches "migration", "migrate" - Boolean operators:
database AND NOT test - Column filters:
tool_name:Editto search only Edit tool observations
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.
- 5d ago First seen · 71 lines · 23 tokens per session scan A 2f1e7043cff4
mem-search is a skill published in the GitHub repository softspark/ai-toolkit (168 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 581 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 skills, from other repositories
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
digital-brain
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
agent-assistant
Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck…
ac-memory-manager
Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.
auto-dream
Background memory consolidation — overnight review, merge, and injection payload for memory files.
ac-knowledge-graph
Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.