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/HybridAIOne/hybridclawnpx agentmods add skills/hybridaione/hybridclaw/distil-pii-redactorWrote 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/hybridaione/hybridclaw/distil-pii-redactor)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/distil-pii-redactor"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/distil-pii-redactor/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/hybridaione/hybridclaw/distil-pii-redactor"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/distil-pii-redactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01041 |
| Opus 5 | $0.00023 | $0.00521 |
| Sonnet 5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
distil-pii-redactor scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distil PII Redactor
Use this skill when the user asks to redact, anonymize, sanitize, or remove PII
or personal data from text. It runs a local Distil-PII GGUF model through
llama-server; raw text must not be sent to external APIs.
Privacy Rules
- Do not quote, summarize, or repeat raw PII in chat.
- Prefer file-based input and output when the sensitive text is already in a file or attachment.
- Return only the redacted text unless the user is explicitly debugging the redactor itself.
- If the user asks for only the LLM or redaction output, do not narrate setup, server status, tool use, or validation details in the final response.
- Do not use
--show-entitiesin normal workflows. It emits original values. - Do not store raw PII in tracked files, shell history, long-lived notes, or logs.
- This skill declares no external credentials. If a downstream tool needs
authentication, use that tool's HybridClaw
secret_refor gateway secret injection and pass only redacted text downstream. - Do not convert raw PII into HybridClaw secrets. Secret refs are for credentials and auth material, not a transport for user data.
Setup
If llama-server is missing, install it with:
hybridclaw skill install distil-pii-redactor llama-server
or install llama.cpp manually. This skill intentionally has no
credentials: frontmatter because local inference does not need API keys; any
future remote-provider variant must declare secret_ref credentials instead of
reading raw environment variables.
Start the local server:
bash skills/distil-pii-redactor/scripts/setup.sh
The setup script stores the model under ~/.hybridclaw/distil-pii by default,
downloads the public Distil-PII 1B GGUF model if missing, and starts
llama-server on 127.0.0.1:8712.
Stop the server:
bash skills/distil-pii-redactor/scripts/stop.sh
Redaction Workflow
For files, keep raw input and redacted output on disk:
python3 skills/distil-pii-redactor/scripts/redact.py \
--input-file sensitive.txt \
--output-file redacted.txt
What ships with it
3 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.
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.
- 13d ago First seen · 139 lines · 46 tokens per session scan A 25470d59c673
distil-pii-redactor is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,041 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
seo-llm
Use when optimizing content for LLM-powered search engines (ChatGPT, Perplexity, Gemini, Claude, Bing AI, Qwen), implementing RAG optimization, prompt engineering for search visibility, semantic SEO, and ensuring content ranks highly in AI-driven search results. Includes techniques for ChatGPT SEO, Perplexity…
langchain
Use when building LLM applications with LangChain, implementing chains, agents, tools, memory, prompts, and retrieval systems. Includes best practices for prompt engineering, tool integration, and agent development. Based on LangChain/LangGraph official documentation and agent development best practices.
ontology-constraint-and-knowledge-injection
A method for deciding how an ontology’s knowledge should reach an AI model: directly in its instructions, through RAG, or through fine-tuning. RAG retrieves relevant information at answer time; fine-tuning changes the model using training examples.
vector-database-engineer
Skill "vector-database-engineer" from frank-luongt/faos-skills-marketplace, covering vector database engineer, do not use this skill when, instructions, capabilities and use this skill when.