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/gotempsh/tempsWrote 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/gotempsh/temps/projects)<a href="https://agentmods.dev/commands/gotempsh/temps/projects"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/projects/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/gotempsh/temps/projects"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/projects.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 | $0.00000 | $0.03301 |
| Opus 5.5 | $0.00000 | $0.01320 |
| Sonnet 5.5 | $0.00000 | $0.00660 |
| Haiku 4.5 | $0.00000 | $0.00330 |
Grade A, and why
projects 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 6d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
projects command reference
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
projects (alias: project, p)
Manage services: each one deployable app (the console calls these Services). To group services that ship together into a Project, as the console calls it, use project-groups.
Subcommands:
secrets- Manage project secrets — mounted into the deployed container as files at /run/secrets/, not environment variables. Distinct fromtemps secrets(agent/MCP-sandbox-scoped).list(ls) - List all servicescreate(new) - Create a new service (git-based or manual deployment); add it to a project withproject-groups addcloudflare-capability(delivery-capability) - Show whether Cloudflare/Bunny delivery is ready and which one new services get by defaultshow(get) - Show service details, including the project (group) it belongs togroup- Show which project (group of services) a service belongs toupdate(edit) - Update service name and descriptionsettings- Update service settings (name, slug, attack mode, preview environments, vulnerability scanning, image retention)git- Update git repository settingssource- Show or change how a service is deployed (primary source, and whether it also acceptsdropuploads)hosting- Show or set whether Temps runs the app (hosted) or it runs elsewhere (external, labelled External and never deployed)config- Update deployment configuration (resources, replicas)delete(rm) - Delete a service
projects secrets
Manage project secrets — mounted into the deployed container as files at /run/secrets/, not environment variables. Distinct from temps secrets (agent/MCP-sandbox-scoped).
Subcommands:
list(ls) - List secrets for a project (values are never returned)create(add) - Create a project secret (mounted at /run/secrets/ on the next deployment)update- Update a project secret (a redeploy is required for running containers to pick it up)delete(rm) - Delete a project secret
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.
- 6d ago Changed · +25 lines 262e3161d737
- 17d ago Changed · +12 lines 5e75b9318ff2
- 1mo ago Changed · +2 lines 4a753b8c9b53
- 1mo ago First seen · 232 lines · 0 tokens per session scan A c6d9774d8be9
projects is a command published in the GitHub repository gotempsh/temps (854 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,301 tokens. 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 2026-09-03.
Other commands, from other repositories
issue-prd-generation
You are generating a comprehensive Product Requirements Document (PRD) for a GitHub issue. This PRD will be passed to a separate AI agent instance with ONLY THIS CONTEXT for implementation. Write with that constraint in mind.
artifact-insight-scan
Analyze the provided project artifacts for missed insights, action items, and follow-ups that should become tracked issues.
start-development
Start development workflow process in Moira.
ccc-makeover
Score project health with X-Ray, apply the top recommendations in impact order with your OK for each, and show the before and after score. Use when you want the highest-impact project health fixes applied and measured.
signal-planner
Closed-loop autonomy — convert a production/analytics/incident signal into a dependency-ordered issue DAG, execute via /orchestrate, then verify the originating signal is resolved. Event-driven companion to /autopilot.
orchestrate
Orchestrate several issues in parallel — launches one lean work-on lane per issue (background shell or agent), GitHub is the register.