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/first-ask)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/first-ask"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/first-ask/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/first-ask"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/first-ask.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 | $0.00012 | $0.00717 |
| Opus 5.5 | $0.00005 | $0.00287 |
| Sonnet 5.5 | $0.00002 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
first-ask 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/first-ask - Understand Before You Build
Do not start implementing until you fully understand the task.
Input
User's request: {{input}}
Step 1: Iterative Refinement
Your goal is to refine your understanding by asking targeted questions and exploring the codebase. Repeat until no unknowns remain.
Ask About
| Category | Key Questions |
|---|---|
| Goal | What is the overall objective? What problem does this solve? |
| Users | Who are the end users? How many? Internal or external? |
| Scope | What are the must-haves (MVP) vs nice-to-haves? |
| Stack | What technologies are in use? Any constraints? |
| Patterns | Are there existing conventions or architecture to follow? |
| Constraints | Performance targets? Security requirements? Timeline? |
| Dependencies | External APIs, databases, services, existing systems? |
| Acceptance | How will we know this is done? What are the success criteria? |
Explore Proactively
Don't just ask -- investigate:
- Scan the codebase for relevant existing code, patterns, and conventions
- Read config files (
package.json,.env.example,pyproject.toml, etc.) - Check existing docs for architecture decisions or constraints
- Research if the task involves unfamiliar libraries or patterns
Refinement Loop
1. Ask specific clarifying questions (not generic ones)
2. Explore the codebase and project structure
3. Summarize your understanding back to the user
4. Ask: "Is there anything I'm missing or got wrong?"
5. Repeat until the user confirms understanding is complete
Keep your understanding as simple as it can be -- avoid overcomplicating.
Step 2: Present Your Plan
Once understanding is clear, present a concise plan:
## Understanding
{2-3 sentences summarizing what you'll build and why}
## Approach
1. {Step 1 - what you'll do first}
2. {Step 2 - next action}
3. {Step 3 - and so on}
## Key Decisions
- {Any architectural or technical decisions made during clarification}
## Out of Scope
- {What you're explicitly NOT doing}
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 · 113 lines · 12 tokens per session scan A 6d9880633eae
first-ask is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 717 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.
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.
accept
Command dispatcher for accept.
change
Command dispatcher for change.
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.