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/new-feature)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/new-feature"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/new-feature/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/new-feature"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/new-feature.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 | $0.00014 | $0.00881 |
| Opus 5.5 | $0.00006 | $0.00352 |
| Sonnet 5.5 | $0.00003 | $0.00176 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
new-feature 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new-feature — Start a New Feature
Begin the automated agent pipeline for a new feature or task.
Input
User's request: {{input}}
If {{input}} is empty, ask: "What feature or task do you want to build? You can provide a detailed description, a rough idea, or reference a backlog item."
Step 1: Assess Input Quality
Evaluate the user's input:
| Input Quality | Indicators | Action |
|---|---|---|
| Vague idea | No specifics, just a concept ("I want search to be better") | → Go to Step 2A (refine with Prompt Engineer) |
| Rough requirements | Some specifics but missing constraints, success criteria | → Go to Step 2A (refine with Prompt Engineer) |
| Clear requirements | Has goal, specifics, and some constraints | → Go to Step 2B (create Intent Document directly) |
| Backlog reference | Points to a file in .caddis/parking-lot/ |
→ Read the parked item, then go to Step 2B |
Step 2A: Refine with Prompt Engineer
The input needs refinement before entering the pipeline.
Intent Documents created or updated in this flow must follow .github/instructions/document-frontmatter.instructions.md.
- Read
skills/workflow/intent-writer/SKILL.md - Follow the skill to structure the input into an Intent Document
- Ask clarifying questions to fill gaps (goal, success criteria, constraints, out of scope)
- Run the framework feasibility pre-check
- Write the Intent Document to
.github/agent-docs/intents/ - Update
.github/agent-docs/ARTIFACTS.md - Present the Intent Document to the user for approval
Step 2B: Create Intent Document Directly
The input is clear enough — structure it without extensive Q&A.
Intent Documents created or updated in this flow must follow .github/instructions/document-frontmatter.instructions.md.
- Read
skills/workflow/intent-writer/SKILL.md - Follow the skill to create the Intent Document
- Run the framework feasibility pre-check
- Write the Intent Document to
.github/agent-docs/intents/ - Update
.github/agent-docs/ARTIFACTS.md - Present the Intent Document to the user for approval
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 · 117 lines · 14 tokens per session scan A 7cce399e4b70
new-feature is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 881 once invoked, about $0.0001 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.
specify
Command dispatcher for specify.
accept
Command dispatcher for accept.
change
Command dispatcher for change.
checklist
Generate a custom checklist for the current feature based on user requirements.