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 aksika/abtars --skill abmind-runtime-operationsgit clone --depth 1 https://github.com/aksika/abtarsWrote 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/aksika/abtars/abmind-runtime-operations)<a href="https://agentmods.dev/skills/aksika/abtars/abmind-runtime-operations"><img src="https://agentmods.dev/badge/skills/aksika/abtars/abmind-runtime-operations.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 5.1 | $0.00026 | $0.01544 |
| Opus 5 | $0.00013 | $0.00772 |
| Sonnet 5 | $0.00005 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
abmind-runtime-operations 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 today.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
abmind Runtime Operations
Use this skill for questions or changes involving the abmind runtime: memory health, persona files, user profile, sleep maintenance, memory backups, encryption, hooks, remote state, or the abmind service.
Safety rules
- Inspect first and distinguish diagnosis from mutation.
- Never edit
memory.dbdirectly. - Never run ad-hoc SQL against the live memory database.
- Database schema and migration changes require specific operator approval.
- Use the abmind CLI for memory, backup, restore, repair, and encryption work.
- Never print, copy, or paste
abmind.key,key.verify, passphrases, or memory contents that were not requested. - Restores, rekeying, attribution repair, bulk memory changes, and sleep application require an explicit operator request.
- Back up before destructive or difficult-to-reverse operations.
Runtime roots
ABMIND_HOME— abmind runtime root; normally~/.abmind/MEMORY_DIR— memory data directory; normally~/.abmind/memory/
Start with read-only checks:
abmind status
abmind doctor
abmind hook-doctor
If abmind is hosted by abtars, also check:
abtars status
abtars doctor
Runtime layout
| Path | Ownership and purpose |
|---|---|
config/.env.memory |
Memory, embedding, retention, and sleep-related environment settings |
config/sleep.json |
Sleep step order, prompt names, budgets, and eligibility |
memory/core/SOUL.md |
Personalized agent identity and persona |
memory/core/user_profile.md |
User preferences and stable profile information |
memory/core/agent_notes.md |
Agent-maintained notes |
memory/core/core_facts.md |
Deployment and operational facts |
memory/core/memory-tools.md |
Memory tool instructions |
memory/memory.db |
SQLite memory database; never edit directly |
memory/memory.db-wal |
SQLite write-ahead log |
memory/memory.db-shm |
SQLite shared-memory file |
memory/daily/ |
Daily consolidation files |
memory/weekly/ |
Weekly consolidation files |
memory/quarterly/ |
Quarterly consolidation files |
memory/sleep/ |
Sleep locks and audit artifacts |
memory/working/ |
Temporary consolidation work |
memory/garbage.json |
Pending garbage-collection information |
prompts/sleep/ |
Source-controlled sleep prompts; refreshed by update |
secret/abmind.key |
Encryption key; never expose |
secret/key.verify |
Key verification material; never expose |
backups/ |
Encrypted abmind backups |
logs/ |
Runtime and sleep logs |
hooks/ |
Hook sidecars and hook errors |
remote/ |
Remote transport and client configuration |
manifest.json |
Install and identity metadata |
~/.local/lib/node_modules/ |
Shared native dependencies outside ~/.abmind/ |
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.
- today First seen · 217 lines · 26 tokens per session scan A 8e73503ba0f5
abmind-runtime-operations is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 1,544 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 2026-09-08.
Other skills, from other repositories
memory-enhancement
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…
research-and-incorporate
Research external topics, create comprehensive analysis, and incorporate learnings into Serena and Forgetful memory systems. Use when you say "research and incorporate {topic}", "study {topic} and add to memory", "deep dive on {topic}", or "learn about {topic} for the project". Works on external concepts, frameworks…
memory-reflexion
Tier 2 episode extraction, the reflexion write path split out of the memory router per ADR-063. Extracts an episode from a completed session log so later sessions can replay what was tried and what it cost. Use when you say extract episode from session, record what happened this session, or re-extract this episode. Do…
using-forgetful-memory
Guidance for using Forgetful semantic memory effectively. Applies Zettelkasten atomic memory principles. Use when deciding whether to query or create memories, structuring memory content, or understanding memory importance scoring. Guidance only. Use when you say "how do I create a memory", "how do I link memories…
encode-repo-serena
Populates the Forgetful knowledge base using Serena's LSP-powered symbol analysis for accurate, comprehensive codebase understanding. Use when you say "encode this repository", "populate forgetful with this codebase", "onboard to this repo", "refresh project understanding", or "build knowledge base for this project".…
exploring-knowledge-graph
Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.