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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/plan)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/plan"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/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/saajunaid/caddis-plugin/plan"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/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 | $0.00009 | $0.04270 |
| Opus 5.5 | $0.00004 | $0.01708 |
| Sonnet 5.5 | $0.00002 | $0.00854 |
| Haiku 4.5 | $0.00001 | $0.00427 |
Grade A, and why
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 1mo 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan - Create Phased Execution Plan
You must create a phased plan document immediately.
Before creating or updating the plan or any supporting Markdown deliverable, apply .github/instructions/document-frontmatter.instructions.md. The YAML frontmatter block must be the first content in the file. New documents require Original Author, Creation Date, and Creating Model; updated documents must preserve those fields and add or update Last Author, Last Updated, and Last Model Used.
Input
User's request: {{input}}
If {{input}} is empty, ask: "What feature or task do you need a phased plan for?"
Step 1: Analyze Scope
Quickly assess the work:
- Read relevant files to understand current state
- Identify components that need creation/modification
- Estimate complexity - is this truly multi-session work?
If work can be completed in ONE session (< 1 hour):
→ Tell user: "This is single-session work. Proceeding directly."
→ Do the work instead of creating a plan.
If work requires MULTIPLE sessions:
→ Continue to Step 2.
Step 1b: Requirements & Constraints
Before designing phases, capture key requirements and constraints that shape the plan:
- REQ-001: [Functional requirement]
- SEC-001: [Security requirement]
- CON-001: [Constraint - tech, time, infrastructure]
- PAT-001: [Pattern to follow from existing codebase]
This ensures nothing is missed during phase design.
Step 2: Design Phases
Break work into independently completable phases:
Phase Sizing Rules
| Phase Size | Guideline |
|---|---|
| Too small | Combined into previous phase |
| Ideal | 30-60 minutes work, clear completion point |
| Too large | Split into sub-phases |
Phase Types (Common Patterns)
Foundation Phase: Data models, adapters, configuration
Core Phase: Business logic, services, main functionality
UI Phase: Pages, components, styling
Integration Phase: Connecting pieces, end-to-end testing
Polish Phase: Error handling, edge cases, documentation
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.
- 1mo ago First seen · 512 lines · 9 tokens per session scan A 616854c0017f
plan is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 4,270 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-09.
Other commands, from other repositories
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.