do
Flagged{"isSafe":false,"isSuspicious":true,"riskLevel":"high","findings":[{"category":"prompt_injection","severity":"high","description":"Explicit prompt injection attempting to override normal operation by claiming the prompt was injected and instructing immediate execution of Step 1, including a STOP READ message.","evidence":"**STOP — DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's plugin system. Using the Read tool on this SKILL.md file wastes ~3,000 tokens. Begin executing Step 1 immediately.**"}],"summary":"The skill content contains a prompt injection attempting to override normal flow and execute steps immediately. There are no malicious shell commands or data exfiltration patterns present, but the injection text itself poses a security risk by attempting to bypass safeguards and coerce the model into acting."}
npx machina-cli add skill SienkLogic/plan-build-run/do --openclawSTOP — DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's plugin system. Using the Read tool on this SKILL.md file wastes ~3,000 tokens. Begin executing Step 1 immediately.
$pbr-do — Freeform Task Router
You are running the do skill. Your job is to analyze freeform text from the user and route it to the most appropriate PBR skill. You are a dispatcher, not an executor — you never do the work yourself.
Step 0 — Immediate Output
Before ANY tool calls, display this banner:
╔══════════════════════════════════════════════════════════════╗
║ PLAN-BUILD-RUN ► ROUTING ║
╚══════════════════════════════════════════════════════════════╝
Then proceed to Step 1.
Step 1 — Validate Input
If $ARGUMENTS is empty, ask the user what they want to do via AskUserQuestion:
What would you like to do? Describe the task, bug, or idea and I'll route it to the right skill.
Step 2 — Analyze and Route
Evaluate $ARGUMENTS against these routing criteria. Apply the first matching rule:
| If the text describes... | Route to | Why |
|---|---|---|
| A bug, error, crash, failure, or something broken | $pbr-debug | Needs systematic investigation |
| Exploration, research, comparison, or "how does X work" | $pbr-explore | Open-ended investigation |
| A complex task: refactoring, migration, multi-file architecture, system redesign | $pbr-plan add | Needs a full phase with research/plan/build cycle |
| A review or quality concern about existing work | $pbr-review | Needs verification against plan |
| A note, idea, or "remember to..." | $pbr-note | Capture for later |
| A specific, actionable task (add feature, fix typo, update config, write test) | $pbr-quick | Self-contained, single executor |
Ambiguity handling: If the text could reasonably match multiple routes, ask the user via AskUserQuestion with the top 2-3 options. For example:
"Refactor the authentication system" could be:
- $pbr-plan add — Full planning cycle (recommended for multi-file refactors)
- $pbr-quick — Quick execution (if scope is small and clear)
Step 3 — Confirm and Dispatch
Display the routing decision:
**Input:** {first 80 chars of arguments}
**Routing to:** {chosen skill}
**Reason:** {one-line explanation}
Then invoke the chosen skill via the Skill tool, passing $ARGUMENTS as the args.
Special case for $pbr-plan add: When routing to plan, check if .planning/ROADMAP.md exists first (via Read). If it doesn't, suggest $pbr-begin instead — the user needs to set up the project before they can add phases.
Step 4 — No Follow-Up
After invoking the skill, your job is done. The dispatched skill handles everything from here (execution, commits, state updates). Do not add any additional output after the Skill tool call.
Source
git clone https://github.com/SienkLogic/plan-build-run/blob/main/plugins/codex-pbr/skills/do/SKILL.mdView on GitHub Overview
The do skill acts as a dispatcher in Plan-Build-Runs. It analyzes freeform user input and routes it to the most appropriate PBR skill, ensuring tasks are handled by the right executor. This reduces misrouting and accelerates the workflow.
How This Skill Works
Technically, it evaluates the user text against a prioritized set of routing rules and uses the first match. The rules map to: bug/crash to pbr-debug; exploration to pbr-explore; complex tasks to pbr-plan add; review to pbr-review; note to pbr-note; quick task to pbr-quick. If multiple rules could apply, it prompts for a top-2 to top-3 choice and then dispatches to the selected skill.
When to Use It
- You describe a software bug, crash, or failure that needs investigation.
- You are exploring or researching how a system works and want an open-ended answer.
- You have a complex task like refactoring or migrating architecture that requires a plan.
- You want a quality check or review of existing work against a plan.
- You have a specific, actionable task such as adding a feature, fixing a typo, updating config, or writing a test.
Quick Start
- Step 1: Describe the task, bug, or idea you want routed.
- Step 2: Let the do skill analyze and suggest the best matching PBR skill using first-match routing.
- Step 3: The chosen skill is invoked to handle the task.
Best Practices
- Describe tasks clearly with the problem, context, and end goal to aid precise routing.
- Use action-oriented language to trigger quick routing to a concrete skill.
- If you intend a specific skill, name it explicitly or surface the top options if unsure.
- Keep prompts focused on a single task to improve dispatch accuracy.
- If routing results are ambiguous, ask for confirmation and present the top options.
Example Use Cases
- I found a crash in the login module and need debugging guidance.
- How does the caching layer work in our service?
- Refactor the authentication service to support a new flow.
- Please review the latest PR for potential issues.
- Note: Remember to add a unit test for the new feature.
