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/functions)<a href="https://agentmods.dev/commands/gotempsh/temps/functions"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/functions/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/functions"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/functions.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 | $0.00956 |
| Opus 5.5 | $0.00000 | $0.00382 |
| Sonnet 5.5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
functions 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
functions command reference
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
functions (alias: fn)
Manage scale-to-zero functions (WASM modules or OCI images) in a project
Subcommands:
capability- Show whether this Temps instance can run functions, and what is missinglist(ls) - List the functions of a projectshow- Show a function (ID or name), including why it is not servingcreate- Create a function from a WASM module or an OCI imagerm(delete) - Delete a function (ID or name)sleep- Stop a running function now; the next request wakes itwake- Start a function now instead of on its next request
functions capability
Show whether this Temps instance can run functions, and what is missing
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
--json |
Output in JSON format | - | No |
functions list (alias: ls)
List the functions of a project
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug | - | No |
--page <n> |
Page number | 1 |
No |
--page-size <n> |
Items per page (max 100) | 20 |
No |
--json |
Output in JSON format | - | No |
functions show
Show a function (ID or name), including why it is not serving
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug | - | No |
--json |
Output in JSON format | - | No |
functions create
Create a function from a WASM module or an OCI image
Options:
| Flag | Description | Default | Required |
|---|---|---|---|
-p, --project <project> |
Project slug | - | No |
--name <name> |
Function name; part of its hostname | - | No |
--wasm <file> |
WASI preview 1 module (wasm32-wasip1) serving HTTP CGI-style | - | No |
--image <ref> |
OCI image reference serving HTTP on --port | - | No |
--port <port> |
Port the function serves on (default 8080) | - | No |
--memory <mb> |
Memory limit in MiB (1-4096) | - | No |
--idle-timeout <seconds> |
Stop after this many idle seconds (10-86400, default 300) | - | No |
--wake-timeout <seconds> |
How long the first request waits for a start (1-300, default 30) | - | No |
--json |
Output in JSON format | - | No |
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.
- 12d ago First seen · 106 lines · 0 tokens per session scan A e25ed22a8461
functions is a command published in the GitHub repository gotempsh/temps (906 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 956 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 2026-10-29.
functions compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| functionsgotempsh/temps | Command | 906 | today | Apache-2.0 | A | 0 | Claude Code |
| la-deployTheLobbi/Claude-m | Command | 19 | 1mo ago | none | A | 22 | Claude Code |
| azure-dotnet-webapp:deploy-webappTheLobbi/Claude-m | Command | 19 | 1mo ago | none | B | 65 | Claude Code |
| terraform-scaffoldQuakedudone94/r19-iannuttall-claude-agents-devops | Command | 51 | 6mo ago | none | A | 0 | Claude Code |
| cost-optimizemythicnoteshed/r16-voltagent-awesome-agent-skills-devops | Command | 47 | 6mo ago | none | A | 0 | Claude Code |
| cost-optimizemixedkindweave/r05-jqueryscript-awesome-claude-code-devops | Command | 42 | 6mo ago | none | A | 0 | Claude Code |
| monitor-setupcentiofficermultiply/r17-behisecc-awesome-claude-skills-devops | Command | 43 | 6mo ago | none | A | 0 | Claude Code |