chitin-moat
Enforce contextual permission boundaries for AI agents based on communication surface. Constrains agent capabilities (exec, file I/O, secrets, messaging) by channel trust level rather than message content, preventing social engineering and prompt injection in group chats. Use when: (1) configuring agent permissions per channel/group, (2) setting up read-only mode for public Discord/Telegram, (3) implementing sovereign/trusted/guarded/observer/silent trust tiers, (4) auditing agent channel permissions, or (5) the user mentions "trust channels", "channel permissions", or "read-only mode."
Best use case
chitin-moat is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Enforce contextual permission boundaries for AI agents based on communication surface. Constrains agent capabilities (exec, file I/O, secrets, messaging) by channel trust level rather than message content, preventing social engineering and prompt injection in group chats. Use when: (1) configuring agent permissions per channel/group, (2) setting up read-only mode for public Discord/Telegram, (3) implementing sovereign/trusted/guarded/observer/silent trust tiers, (4) auditing agent channel permissions, or (5) the user mentions "trust channels", "channel permissions", or "read-only mode."
Teams using chitin-moat should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/chitin-moat/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How chitin-moat Compares
| Feature / Agent | chitin-moat | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Enforce contextual permission boundaries for AI agents based on communication surface. Constrains agent capabilities (exec, file I/O, secrets, messaging) by channel trust level rather than message content, preventing social engineering and prompt injection in group chats. Use when: (1) configuring agent permissions per channel/group, (2) setting up read-only mode for public Discord/Telegram, (3) implementing sovereign/trusted/guarded/observer/silent trust tiers, (4) auditing agent channel permissions, or (5) the user mentions "trust channels", "channel permissions", or "read-only mode."
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Chitin Moat
Enforce contextual agent permissions based on where a conversation happens.
## Trust Levels
| Level | Name | Capabilities |
|-------|------|-------------|
| 0 | `sovereign` | Full autonomy (1:1 with verified owner) |
| 1 | `trusted` | Read/write, scoped tools, no secrets (private known group) |
| 2 | `guarded` | Respond on @mention only, no tools (semi-public) |
| 3 | `observer` | React only (public channels) |
| 4 | `silent` | No interaction (blocked surfaces) |
## Configuration
Create `chitin-trust-channels.yaml` in the agent workspace root:
```yaml
version: "0.1"
owner:
telegram: "<owner_user_id>"
channels:
- id: "telegram:<owner_user_id>"
level: sovereign
- id: "discord:<server_id>"
level: guarded
overrides:
- channel: "owners-lounge"
level: trusted
- channel: "pro-*"
level: trusted
- id: "telegram:group:*"
level: observer
defaults:
unknown_channel: observer
unknown_dm: guarded
```
## Setup
1. Copy the example config: `cp references/example-config.yaml chitin-trust-channels.yaml`
2. Edit with your channel IDs and owner identity
3. Run the validator: `python3 scripts/validate_config.py chitin-trust-channels.yaml`
4. Run the audit: `python3 scripts/audit_channels.py chitin-trust-channels.yaml`
## Permission Matrix
See `references/permission-matrix.md` for the full capability × trust-level matrix.
## Scripts
- `scripts/validate_config.py <config>` — Validate a trust channels config file
- `scripts/audit_channels.py <config>` — Audit current channel bindings against the config and report mismatches
- `scripts/resolve_channel.py <config> <channel_id>` — Resolve the trust level for a specific channel ID
## Integration with AGENTS.md
Add to the agent's workspace instructions:
```markdown
## Chitin Moat
Before responding in any channel, resolve the trust level using `chitin-trust-channels.yaml`.
Constrain capabilities to the resolved level. Never escalate beyond the channel ceiling.
```Related Skills
chitin-core
Route tasks to the cheapest capable model. Never crash on rate limits.
Chitin Editorial — Multi-Agent Content Management
**Version:** 1.0.0
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.