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/pool-promote)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/pool-promote"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/pool-promote/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/pool-promote"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/pool-promote.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 | $0.00015 | $0.00290 |
| Opus 5.5 | $0.00006 | $0.00116 |
| Sonnet 5.5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
pool-promote 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.
What it actually says
/pool-promote
Use the pool promotion primitive instead of editing the pool manually.
What to do
- Run
junai pool diff --project <project-path>and identify only reusable managed changes. - Keep the default choice conservative: if a change is not clearly reusable, keep it local.
- Promote only the selected managed paths with
junai pool promote --project <project-path> --reason "<why this belongs in the pool>". - Stop on the created
promote/<project-name>-<YYYYMMDD>branch and review it before any merge. - If the reusable change came from CI knowledge capture, use
junai pool nuggets review --project <project-path>first so the durable lesson is written into a managed target before promotion.
Rules
- Never promote
agent-docs/,handoffs/,plans/,.pool-version, or other project-owned files. - Never promote private or profile-excluded resources.
- For
copilot-instructions.md, only the marker-managed region is promoted. - Treat the promotion commit as provenance: include the source project and the reason.
- Do not auto-mirror project changes back to the pool outside this explicit review flow.
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 · 26 lines · 15 tokens per session scan A a3dba3f7a8b8
pool-promote is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 290 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
upstream-watch
Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.
swarm-pr
Create and manage AI swarms directly from GitHub Pull Requests, enabling seamless integration with your development workflow.
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.
prototype
Command dispatcher for prototype.
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.