Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/kastheco/claude-plugins/startgit clone --depth 1 https://github.com/kastheco/claude-pluginsWhat 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 | $0.00000 | $0.00493 |
| Opus 5 | $0.00000 | $0.00246 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
start 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kas:start - Structured Planning Workflow
Entry point for creating implementation plans with proper workflow enforcement.
Usage
/kas:start # Start planning for current task
/kas:start "Add user auth" # Start with specific task description
Workflow
Step 1: Enter Plan Mode
If not already in plan mode, use the EnterPlanMode tool to request plan mode from user.
If already in plan mode: Skip this step, continue with current plan file.
Step 2: Explore Phase
Launch Explore agents (1-3 based on scope) to gather codebase context:
- Existing implementations and patterns
- Related components and dependencies
- Testing patterns
On explore failure: Report findings so far, ask user how to proceed.
Step 3: Design Phase
Launch Plan agent with:
- Exploration findings from Step 2
- User requirements
Step 4: Review & Finalize
- Read critical files identified by agents
- Validate alignment with user intent
- Ask clarifying questions via AskUserQuestion if needed
- Write final plan to plan file
Step 5: Review Agent (Auto-triggered)
After plan is written, ALWAYS run before ExitPlanMode:
- plan-reviewer - Check for security gaps, design flaws
Step 6: Exit Plan Mode
Call ExitPlanMode to present to user:
- The plan
- Review findings
Error Handling
| Failure | Response |
|---|---|
| Already in plan mode | Use existing plan file, continue workflow |
| Explore agent fails | Report partial findings, ask user direction |
| User rejects at review | Ask what to revise, update plan |
| plan-reviewer finds blockers | Show findings, do NOT call ExitPlanMode until resolved |
Integration Contract (for 3rd Party Skills)
Skills invoking /kas:start can depend on:
Guaranteed after completion:
- Plan mode was active during planning
- Plan file exists at
.claude/plans/<name>.md - plan-reviewer ran (findings available)
- User approved via ExitPlanMode
Side effects:
- Plan file written
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.
- yesterday First seen · 81 lines · 0 tokens per session scan A 09bf94f04ca6
start is a command published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 493 tokens. 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.