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.
git clone --depth 1 https://github.com/abossenbroek/abossenbroek-claude-pluginsWrote 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/commands/abossenbroek/abossenbroek-claude-plugins/optimize-plan)<a href="https://agentmods.dev/commands/abossenbroek/abossenbroek-claude-plugins/optimize-plan"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/optimize-plan/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/commands/abossenbroek/abossenbroek-claude-plugins/optimize-plan"><img src="https://agentmods.dev/badge/commands/abossenbroek/abossenbroek-claude-plugins/optimize-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00544 |
| Opus 5 | $0.00000 | $0.00272 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
optimize-plan 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 8d 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.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/optimize-plan Command
Optimize a plan file for efficient context management and agent handoffs.
Usage
/optimize-plan [path]
Arguments
path (optional):
- Path to plan file (default: most recent plan in
.claude/plans/)
Instructions
You are the MINIMAL entry point for plan optimization. Your ONLY job is to:
- Locate the plan file to optimize
- Launch the plan-coordinator agent
- Return the coordinator's output directly
Step 1: Locate Plan
If no path provided:
- Look in
.claude/plans/for recent.mdfiles - If multiple found, use most recently modified
- If none found, ask user to provide path
Verify the plan exists by attempting to read it.
Step 2: Launch Coordinator
Use the Task tool to launch the plan-coordinator agent:
Task: Optimize plan for context efficiency
Agent: agents/plan-coordinator.md
Prompt:
plan_path: [resolved plan file path]
The coordinator will:
- Analyze plan structure and phases
- Map context flows between phases
- Identify optimization opportunities
- Present options for user selection
- Generate optimized version with comparison
Step 3: Return Output
Return the coordinator's output DIRECTLY to the user.
DO NOT:
- Add commentary about the process
- Explain what the coordinator did
- Include intermediate analysis
- Modify the output
ONLY return the final optimized plan and comparison.
Context Isolation Rules
This command is the FIREWALL between main session and optimization work:
- Main session context stays CLEAN
- Only plan path passes to coordinator
- Only the final output returns to user
- No intermediate analysis enters main context
Examples
/optimize-plan
# Optimizes most recent plan in .claude/plans/
/optimize-plan ~/.claude/plans/my-feature-plan.md
# Optimizes specific plan file
What Gets Optimized
Context Tiers
- Assign appropriate context tiers to each phase
- Identify phases using higher tier than needed
- Add explicit tier specifications
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.
- 8d ago First seen · 106 lines · 0 tokens per session scan A 39925e94237b
optimize-plan is a command published in the GitHub repository abossenbroek/abossenbroek-claude-plugins (2 stars, last pushed 4mo ago), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 544 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.