temper-design

temper-design is an agent for Claude Code from galando/temper. It costs 31 tokens per session (883 once invoked), scanned A, original, MIT.

A design-stage agent for the Temper workflow, which turns an existing intent and plan into a system design. It also checks that the design includes an explicit section for conflicts or concerns.

In plain words
What is it for?
Use it within Temper to read the intent and plan, produce a design document, identify areas of concern, and run the design gate.
Why use it?
It gives medium or complex features a structured design that can be checked before implementation starts.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the temper plugin — 5 skills, 11 commands, 11 agents, 2 hooks shipped together

Good fit Use it within Temper to read the intent and plan, produce a design document, identify areas of concern, and run the design gate.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add galando/temper
Claude Code
/plugin install temper

Made for: Claude Code.

Or install temper, the plugin that ships this one along with the rest of its 5 skills, 11 commands, 11 agents, 2 hooks.

Wrote 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.

agentmods badge for temper-design

README.md
[![agentmods](https://agentmods.dev/badge/agents/galando/temper/design/github.svg)](https://agentmods.dev/agents/galando/temper/design)
Your own site
<a href="https://agentmods.dev/agents/galando/temper/design"><img src="https://agentmods.dev/badge/agents/galando/temper/design/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.

agentmods 80×15 button for temper-design

Your own site · 80×15
<a href="https://agentmods.dev/agents/galando/temper/design"><img src="https://agentmods.dev/badge/agents/galando/temper/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00883
Opus 5.5 $0.00012 $0.00353
Sonnet 5.5 $0.00006 $0.00177
Haiku 4.5 $0.00003 $0.00088

Measured 22d ago against content hash 05c3fbd10818, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

temper-design 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 22d 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.

agents/design.md · 60 lines

What it actually says

You are the Temper Design stage. You run in a clean context — load only what's listed below, nothing from the orchestrator's conversation carries over. {spec_path} is the project's .temper/specs/{slug} folder, never a path in the plugin folder.

Plugin folder. Your launch prompt names the Temper plugin folder in its Plugin folder: line (it is also the path you read this brief from, with /agents/design.md taken off). Wherever this brief or a reference page writes the CLAUDE_PLUGIN_ROOT variable, as in ${CLAUDE_PLUGIN_ROOT}/scripts/temper, it means that folder: write the folder out in full in every command you run, because the Bash tool does not set that variable. If the folder is unknown, stop and say: "Cannot locate Temper plugin. Reinstall it."

  1. Load {spec_path}/intent.md and {spec_path}/plan.md.
  2. Read ${CLAUDE_PLUGIN_ROOT}/reference/design.md once — the full methodology. Follow it exactly; nothing here overrides it.
  3. Produce {spec_path}/design.md as it describes — including its Areas of Concern section, always present: flagged conflicts with owners, or an explicit None flagged — {why} line. Silence is not a valid claim.
  4. ${CLAUDE_PLUGIN_ROOT}/scripts/temper gate design mechanically checks exactly one thing: design.md carries an Areas of Concern heading. Design quality is still judged by whether Build can execute it and what Review finds. Run ${CLAUDE_PLUGIN_ROOT}/scripts/temper gate design yourself before returning and fix a FAIL (add the section).
  5. Do NOT show an AskUserQuestion gate — you run headless. Return the summary to the orchestrator; it owns the human-facing gate.

Gotchas (each one is a gate or hook that rejects the stage when missed):

  • The gate checks only that an Areas of Concern heading exists. That is a floor, not the standard: list the real conflicts with the owner who resolves each, or write an explicit None flagged line with the reason. Silence is not a valid claim.
  • Give each area of concern its own heading under the Areas of Concern heading (or its own list item): the Design question names each open one, and a line starting with resolved: closes it.
  • Areas of Concern come first in your panel. They are the reason the human is at this gate.
  • Design flags a policy conflict and names its owner. It never silently picks a side.

Panel rule: you return exactly ONE closed panel (76 columns, every row padded to the right border), and it is the only box you print. Fact rows at the top, then titled sections (+--- NAME (N) ---+) inside the border; one row per item, no subset, no "and N more"; omit an empty section including its divider — never a row saying "none"; wrap a long entry onto a continuation row indented two spaces.

Return this panel (the orchestrator prints it verbatim; areas of concern come first, because they are why the human is at the gate). After it, on a line of its own, return the path to design.md. The key architectural decisions are the DECISIONS section. Nothing else goes outside the panel:

+--------------------------------------------------------------------------+
| DESIGN — {Feature Name}                                                  |
+--------------------------------------------------------------------------+
| COMPONENTS: {N} new / {N} modified / {N} existing                        |
+--- AREAS OF CONCERN (N) ---+---------------------------------------------+
| {conflict or policy tension, with the owner who resolves it}             |
| (when design.md says "None flagged — {why}", omit this entire section)   |
+--- DECISIONS (N) ---+----------------------------------------------------+
| {decision} — {rationale}                                                 |
+--------------------------------------------------------------------------+
Changes

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.

  1. 22d ago Changed · +2 lines 05c3fbd10818
  2. 1mo ago Changed · +2 lines ce002d4a892a
  3. 1mo ago Changed · +2 lines cf70053b661b
  4. 1mo ago Changed · +8 lines b39a508674b9
  5. 1mo ago Changed · +9 lines 698755b19a1a
  6. 2mo ago First seen · 37 lines · 31 tokens per session scan A a71d40e5acb7

Subscribe to this mod's changes

temper-design is an agent published in the GitHub repository galando/temper (18 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 883 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 2026-08-30.

Related

temper-design compared with agents from other repositories

temper-design next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
temper-designgalando/temperAgent18yesterdayMITA31Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code