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/relay)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/relay"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/relay/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/relay"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/relay.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 | $0.01349 |
| Opus 5.5 | $0.00005 | $0.00540 |
| Sonnet 5.5 | $0.00002 | $0.00270 |
| Haiku 4.5 | $0.00001 | $0.00135 |
Grade A, and why
relay 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/relay - Session Continuation Document
Create or update a generic relay.md file at the target repository root so a future session can quickly understand the project, the current workstream, and the exact next step.
This prompt is repository-agnostic. Do not assume a framework, branch strategy, documentation folder, plan folder, or application domain. Discover the current repository shape from files that actually exist.
Input
User input: {{input}}
If the user names a specific task, workstream, branch, or plan, use it as the focus. If not, infer the most likely active workstream from the current conversation, changed files, visible project plans, and current repository state.
Step 1: Inspect The Repository
Gather only verified facts. Prefer lightweight scans before reading large files.
- Identify the repository root.
- Check git state when available:
git status --shortgit branch --show-currentgit log --oneline -5
- Read high-signal root files when present, such as
README.md,CHANGELOG.md,STACK.md, package/build files, or project configuration files. - Search for active plans, roadmaps, TODO files, issue trackers, or architecture notes. Do not assume folder names; inspect what exists.
- Identify validation commands from package scripts, makefiles, task runners, CI files, or documented commands.
- Verify every file path before listing it in
relay.md.
Do not invent paths, commands, phases, owners, or completion state. Mark unknowns explicitly.
Step 2: Determine The Relay Context
Summarize:
- product or project goal
- current project context
- completed work that is visible from plans, docs, git history, or changed files
- current plan or workstream
- exact next step
- important files to read first
- validation state and commands
- blockers, assumptions, and open questions
If multiple plans exist, identify the active one by evidence: recent edits, checked-off progress, current user instruction, or current git changes. If the active plan is ambiguous, say so and list the likely candidates.
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 · 155 lines · 12 tokens per session scan A f5822f48f283
relay 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 1,349 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
claude-flow-memory
Interact with Claude-Flow memory system.
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.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.