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 tolgakisaogullari/SumelaOS --skill qdrant-session-memorygit clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSWrote 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/tolgakisaogullari/sumelaos/qdrant-session-memory)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/qdrant-session-memory"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/qdrant-session-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.
<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/qdrant-session-memory"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/qdrant-session-memory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.01697 |
| Opus 5 | $0.00019 | $0.00848 |
| Sonnet 5 | $0.00008 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
qdrant-session-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.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tier-1: Qdrant Session Memory
Important: No API Key Required for Queries
All query operations read from the local Qdrant database via query-qdrant.py. They are purely local — no external API calls, no cost. API keys are only needed for embedding generation via Ollama (which runs locally).
Proactive Usage (Silent)
The agent should query Qdrant without waiting for the user to ask in these scenarios:
Before Starting a Task
When the user assigns a new task, check if similar work was done before:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<task description>" --limit 3
- If top score ≥ 0.5: read the matching session summary for context, lessons learned, and decisions made
- If score < 0.5: skip — no relevant past context
When Encountering an Entity or Concept
When the task involves an entity, service, or concept that might have been discussed before:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<entity name> <context>" --limit 3
Example: Task mentions "CommentService" → query "CommentService design decisions"
When Making Architectural Decisions
Before proposing an architecture or design choice, check if similar decisions were made:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<decision topic>" --limit 3
Example: "caching strategy" → check if caching was discussed before
When Debugging
Before diving into a bug, check if similar issues were encountered:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<bug description or error message>" --limit 3
When a File is Mentioned
When the task involves a specific file that might have history:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<filename> changes" --limit 3
RULE: This is SILENT — do not announce "I'm checking past sessions via Qdrant" unless the user explicitly asks. Just query, read relevant context, and incorporate into your analysis.
What ships with it
11 files 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.
- README.md 8.9 KB
- requirements.txt 196 B
- scripts/delete-from-qdrant.py 2.9 KB runs code
- scripts/ingest-code-to-qdrant.py 22 KB runs code
- scripts/ingest-wiki-to-qdrant.py 17 KB runs code
- scripts/lib/memory_ingest.py 27 KB runs code
- scripts/migrate-collections.py 23 KB runs code
- scripts/query-qdrant.py 20 KB runs code
- scripts/resolve-ingest-dirs.py 1.1 KB runs code
- scripts/session-ingest.py 15 KB runs code
- scripts/setup-qdrant.py 3.7 KB runs code
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.
- 10d ago First seen · 123 lines · 39 tokens per session scan A e08cf356fb2c
qdrant-session-memory is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 16d ago), licensed MIT. It adds 39 tokens to every session and 1,697 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.