From sentinel
Generate tool boundary declarations from an approved routing report. Use when the developer says "boundary", "load tools", "apply routing", "generate boundaries", or after approving a routing report. CRITICAL ROUTING RULE: This skill runs AFTER /sentinel:routing — it requires docs/tool-routing-report.md with status:approved. If no approved routing report exists, tell the user to run /sentinel:routing first. Never run boundary before routing. When NOT to use: For scanning/classifying which skills a project needs, use /sentinel:routing instead. Boundary does not decide which tools to include — it only generates boundary declarations for tools already approved in the routing report. Input: an approved docs/tool-routing-report.md (generated by /sentinel:routing). Output: .claude/rules/tool-boundary.md containing per-tool capability/limitation declarations, chain patterns, and failure behaviors. Preserves manual edits marked with <!-- manual -->. Edge cases: if routing report exists but is not approved, STOPs with guidance. If tool-boundary.md already exists, updates it (preserving manual sections).
How this skill is triggered — by the user, by Claude, or both
Slash command
/sentinel:boundaryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read the approved routing report and generate/update tool boundary declarations in `.claude/rules/`.
Read the approved routing report and generate/update tool boundary declarations in .claude/rules/.
Prerequisite: docs/tool-routing-report.md must exist with status: approved.
Read docs/tool-routing-report.md. If it does not exist or status is not approved:
/routing first, or to mark the report as approvedRead the following to understand usage patterns:
CLAUDE.md (root)ARCHITECTURE.md or docs/architecture.md (if exists)docs/tool-routing-report.md (the approved routing report).claude/rules/tool-boundary.md (if exists — this is an UPDATE).claude/rules/tool-boundary.mdIf the file already exists, update it. If not, create it.
For each included skill/tool, write a boundary declaration based on:
Use this structure:
# Tool Boundaries — {project name}
> Auto-generated by /boundary on {YYYY-MM-DD}
> Source: docs/tool-routing-report.md (approved {date})
> Update by running /boundary again after modifying the routing report.
## Project Scope Declaration
This project uses the following tools. Skills not listed here are global noise — deprioritize them.
### Skills
#### {skill-name}
- **Purpose in this project:** {one sentence from routing report rationale}
- **Can do:** {capabilities}
- **Cannot do:** {limitations}
- **Input constraints:** {what it needs to work}
- **Chain pattern:** {if multi-step, declare the sequence}
- **Failure behavior:** {what to do if it fails}
#### {next skill}
...
### MCP Tools
#### {mcp-server-name}
| Tool | Can do | Cannot do | Input constraints |
|------|--------|-----------|-------------------|
| {tool_name} | ... | ... | ... |
**Chain pattern:** {sequence if multi-step}
**Key boundary:** {most important limitation to remember}
### CLI Tools
#### {cli-tool-name}
- **Purpose in this project:** ...
- **Invocation:** {command pattern}
- **Constraints:** ...
## Escape Hatch
If a routing rule or boundary declaration causes repeated failures (3+ consecutive), fall back to asking the developer rather than following the stale rule. Report the failure pattern so the developer can update the routing report.
After generating/updating:
Tell the developer:
.claude/rules/tool-boundary.mddocs/tool-routing-report.md → re-approve → run /boundary again<!-- manual --> markers)npx claudepluginhub touricks/fanshi_personal_skills --plugin sentinelGenerates .claude/BOUNDARIES.md from a discovery document's Module Structure section to enforce module boundaries in greenfield projects.
Routes every agent action through correct skills via routing table before code, files, or technical decisions. Checks adaptive overrides; defaults to rune:cook for code tasks.
Restructures oversized single-file Skills or scattered project rules into a well-organized Skill directory with progressive rigor tiers.