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/krmcbride/claude-plugins/ultraplangit clone --depth 1 https://github.com/krmcbride/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 | $0.00014 | $0.02645 |
| Opus 5 | $0.00007 | $0.01323 |
| Sonnet 5 | $0.00003 | $0.00529 |
| Haiku 4.5 | $0.00001 | $0.00265 |
Grade A, and why
ultraplan 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 2d 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 — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UltraPlan Investigation Workflow
Conduct a deep, systematic investigation of the following problem using the UltraPlan methodology. This approach prevents shallow analysis by enforcing multiple investigation steps with progressive confidence building.
Problem to investigate: $ARGUMENTS
Investigation Framework
Confidence Levels
Create a TODO list to track your confidence explicitly at each step. Progress through these levels as evidence accumulates:
- exploring - Initial reconnaissance, forming hypotheses
- low - Have basic understanding, significant unknowns remain
- medium - Core patterns identified, some uncertainties
- high - Strong evidence, validated through multiple checks
- very_high - Comprehensive understanding, minor gaps only
- almost_certain - Exhaustive investigation, ready to conclude
- certain - Complete confidence, no further investigation needed
Investigation State
Maintain this state structure throughout the investigation:
{
"step_number": 1,
"confidence": "exploring",
"findings": ["Discovery or insight from this step"],
"relevant_files": ["/absolute/path/to/file.ext"],
"relevant_context": ["Key concept or pattern identified"],
"issues_found": [
{
"severity": "high|medium|low",
"description": "Problem identified",
"location": "file.ext:123"
}
],
"hypotheses": [
{
"step": 1,
"hypothesis": "Initial theory",
"status": "testing|confirmed|rejected|refined"
}
]
}
Workflow Steps
Step 1: Initial Investigation (Confidence: exploring)
Focus on:
- Understanding the technical context and architecture
- Identifying key assumptions to challenge
- Forming initial hypotheses
- Gathering baseline evidence
Actions:
- Read relevant files
- Check configurations and dependencies
- Review logs, errors, or metrics if applicable
- List what you know vs. what you need to discover
When done: Use a Haiku agent as your investigation guide with these instructions:
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.
- 2d ago First seen · 425 lines · 14 tokens per session scan A 59066928067b
ultraplan is a command published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 2,645 once invoked, about $0.0001 per session on Opus 5. 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.