Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/acnlabs/OpenPersonanpx agentmods add skills/acnlabs/openpersona/persona-knowledgeWrote 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/acnlabs/openpersona/persona-knowledge)<a href="https://agentmods.dev/skills/acnlabs/openpersona/persona-knowledge"><img src="https://agentmods.dev/badge/skills/acnlabs/openpersona/persona-knowledge.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 Rogue Agent · line 6 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 116 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00062 | $0.03311 |
| Opus 5 | $0.00031 | $0.01656 |
| Sonnet 5 | $0.00012 | $0.00662 |
| Haiku 4.5 | $0.00006 | $0.00331 |
Grade A, and why
persona-knowledge 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
persona-knowledge
Persistent, incremental, searchable persona knowledge base — the data layer between raw sources and persona training.
Architecture: MemPalace (storage + search) + Knowledge Graph (relationships + timeline) + Karpathy LLM Wiki (knowledge accumulation)
Dependency chain: data sources → persona-knowledge → anyone-skill / persona-model-trainer
When to use this skill
Trigger phrases:
- "create a dataset for this persona"
- "add data to the dataset"
- "import my Obsidian vault"
- "import my Twitter archive"
- "build a knowledge base for X"
- "export training data"
- "search the persona dataset"
Not suitable when:
- User wants a quick one-shot distillation without persistent storage (use anyone-skill alone)
- User only has < 50 messages of data (too little to warrant a dataset)
Phase 1: Init
Create a new persona dataset:
python scripts/init_knowledge.py --slug {slug} --name "Display Name"
This creates ~/.openpersona/knowledge/{slug}/ with:
~/.openpersona/knowledge/{slug}/
dataset.json # metadata: slug, name, created_at, stats
.mempalace/ # MemPalace local data (per-dataset isolation via palace_path)
palace/ # MemPalace internal store (ChromaDB + KG)
sources/ # immutable source file backups
.source-index.json # per-file metadata: hash, import time, line count, PII flags
wiki/ # Karpathy wiki (LLM-maintained derived artifact)
_schema.md # wiki maintenance rules
identity.md
voice.md
values.md
thinking.md
relationships.md # generated from Knowledge Graph
timeline.md # generated from Knowledge Graph
_contradictions.md
_changelog.md
_evidence.md
MemPalace palace structure:
- One Wing per persona (named by slug)
- Halls mapped to 5 persona dimensions:
hall_facts— Identity (background, career, education)hall_events— Memory (key events, turning points)hall_preferences— Personality (values, preferences, boundaries)hall_discoveries— Procedure (mental models, decision heuristics)hall_voice— Interaction (vocabulary, rhythm, humor, emotional temperature)
What ships with it
16 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.
- .gitignore 173 B
- adapters/__init__.py 2.3 KB runs code
- adapters/chat_export.py 5.9 KB runs code
- adapters/social.py 6.6 KB runs code
- adapters/universal.py 14 KB runs code
- CHANGELOG.md 2.1 KB
- publish.sh 1.8 KB runs code
- README.md 5.9 KB
- references/source-formats.md 6.7 KB
- references/wiki-schema.md 4.1 KB
- scripts/export_training.py 21 KB runs code
- scripts/ingest.py 15 KB runs code
- scripts/init_knowledge.py 10 KB runs code
- scripts/lint_wiki.py 8.4 KB runs code
- scripts/query_kg.py 8.7 KB runs code
- tests/test_scripts.py 23 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.
- 8d ago First seen · 357 lines · 62 tokens per session scan A 7e06aa8768d5
persona-knowledge is a skill published in the GitHub repository acnlabs/OpenPersona (49 stars, last pushed 27d ago), licensed MIT. It adds 62 tokens to every session and 3,311 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 2026-08-30.
Other skills, from other repositories
memory-consolidate
A memory-maintenance skill that stores a small number of durable, searchable facts and keeps the main memory file concise.
company-agent-infrastructure
Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…
add-compact
Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
lobu
Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.
add-qmd
Add QMD (Query Markup Documents) as an advanced memory search backend. Upgrades the built-in grep-based memorysearch with hybrid BM25 + vector semantic search + LLM re-ranking. Fully local, no API keys needed. Triggers on "add qmd", "qmd memory", "semantic memory search", "upgrade memory".
clawdi
Use Clawdi Cloud for missing user memory, past sessions, Project or Vault context, Clawdi share URLs, and connected-service fallback such as Gmail, GitHub, Notion, Drive, or Calendar. Prefer an authenticated official service CLI; otherwise choose a trusted direct MCP, safely installable official CLI, official API or…