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/SummerSec/AI-Inner-Osnpx agentmods add skills/summersec/ai-inner-os/user-profile-distillationWrote 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/summersec/ai-inner-os/user-profile-distillation)<a href="https://agentmods.dev/skills/summersec/ai-inner-os/user-profile-distillation"><img src="https://agentmods.dev/badge/skills/summersec/ai-inner-os/user-profile-distillation/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/summersec/ai-inner-os/user-profile-distillation"><img src="https://agentmods.dev/badge/skills/summersec/ai-inner-os/user-profile-distillation.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 | $0.00042 | $0.00705 |
| Opus 5 | $0.00021 | $0.00352 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
user-profile-distillation 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Profile Distillation
Core Rule
This skill is opt-in only. Do not use it unless the user explicitly asks for user profiling, personality/work-style analysis, prompt-history distillation, or similar wording.
Do not read local history, transcripts, databases, or cached prompts unless the user explicitly asks you to do so for this profile task.
Inputs
Use one of these sources:
- User-provided prompts: analyze only the text the user pasted in the current conversation.
- Local history extraction: only after explicit user approval, use the bundled
agent-chat-historyskill to extract user prompts.
For local history, prefer a bounded date range. If no date range is provided, ask for one before reading history.
Recommended command from skills/agent-chat-history/:
python scripts/query_history.py --date YYYY-MM-DD --prompts-only --json
Use --mode claude, --mode codex, or --mode cursor when the user limits the source.
Privacy Boundaries
- Do not infer protected attributes such as race, ethnicity, religion, sexuality, health status, disability, political affiliation, or precise age.
- Do not diagnose mental health, personality disorders, intelligence, or clinical traits.
- Do not quote long prompt excerpts. Use short paraphrases or brief fragments only when necessary.
- Do not save the profile to files, memory, rules, personas, or plugin config unless the user explicitly asks to save it.
- Treat all conclusions as provisional and based only on the provided prompt sample.
Analysis Method
- Identify the data source, date range, client/source, and sample size.
- Remove obvious tool output, copied logs, code blocks, and assistant text when they are not user intent.
- Cluster prompts by task type and recurring intent.
- Distill behavioral patterns with evidence strength:
- strong: repeated across many prompts
- medium: appears several times
- weak: plausible but sparse
- Separate observed behavior from inference. Mark uncertainty clearly.
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 · 99 lines · 42 tokens per session scan A 81bcd2f00389
user-profile-distillation is a skill published in the GitHub repository SummerSec/AI-Inner-Os (17 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 705 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 2026-08-30.
Other skills, from other repositories
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
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.…
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.