A coding-agent add-on that organizes AI-generated software work around intent, planning, testing, review, and quality checks.

Use its commands and agents to define a feature, design and plan it, build with TDD, review the diff, run tests and security checks, fix issues, and package the result.

It helps connect the requested outcome to the code and provides checks intended to catch defects and unintended effects before delivery.

temper — Plugin for Claude Code by galando

Install

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.

Clone the repo

git clone --depth 1 https://github.com/galando/temper

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/galando/temper/temper/github.svg)](https://agentmods.dev/plugins/galando/temper/temper)

Your own site

<a href="https://agentmods.dev/plugins/galando/temper/temper"><img src="https://agentmods.dev/badge/plugins/galando/temper/temper/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/galando/temper/temper"><img src="https://agentmods.dev/badge/plugins/galando/temper/temper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 5 skills, 11 commands, 11 agents, 2 hooks cost 751 tokens a session between them.

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.

Security

Grade A, and why

temper 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 4d 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.

.claude-plugin/plugin.json · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "temper",
  "displayName": "Temper",
  "description": "Claude cannot write code before you approve the intent. Gated plan, TDD, review and check for AI written code, with a phase bar in Claude Code.",
  "version": "9.7.6",
  "author": {
    "name": "galando",
    "url": "https://github.com/galando"
  },
  "repository": "https://github.com/galando/temper",
  "homepage": "https://github.com/galando/temper",
  "license": "MIT",
  "keywords": [
    "intent-driven-development",
    "sdlc",
    "guardrails",
    "tdd",
    "code-review",
    "quality-gates",
    "blast-radius",
    "workflow",
    "enforcement",
    "plan-mode"
  ],
  "commands": [
    "./commands/temper.md",
    "./commands/intent.md",
    "./commands/plan.md",
    "./commands/design.md",
    "./commands/build.md",
    "./commands/review.md",
    "./commands/check.md",
    "./commands/fix.md",
    "./commands/pack.md",
    "./commands/status.md",
    "./commands/init.md"
  ],
  "agents": [
    "./agents/intent.md",
    "./agents/plan.md",
    "./agents/plan-review.md",
    "./agents/design.md",
    "./agents/build.md",
    "./agents/build-task.md",
    "./agents/review.md",
    "./agents/check.md",
    "./agents/rca.md",
    "./agents/fix.md",
    "./agents/pipeline.md"
  ],
  "skills": [
    "./skills/temper-core",
    "./skills/context-engineering",
    "./skills/source-driven-development",
    "./skills/grill-me",
    "./skills/teach-me"
  ],
  "types": "./types/index.d.ts",
  "userConfig": {
    "uiMode": {
      "type": "string",
      "title": "Temper UI mode",
      "description": "How much Temper draws: full, minimal or off. The gate questions, the denials and the subcommands are the same in every mode.",
      "default": "full",
      "sensitive": false
    },
    "enforcement": {
      "type": "string",
      "title": "Temper enforcement",
      "description": "on refuses writes outside the stage, --no-verify, a changed hooks path, and a step only the person may take without their a

Read the full file on GitHub · 97 lines

Contents

What it installs

The manifest is a name and a version. 5 skills, 11 commands, 11 agents, 2 hooks travel with it, and installing the plugin installs all of them — 751 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 656 B

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.

4d ago Changed · +1 lines 01b560427d70
5d ago Changed · +1 lines 8d75e9b05a5e
16d ago Changed 8c48622b8ec4
17d ago Changed 3a1632843975
19d ago Changed f3ce8e638f07
22d ago Changed · -13 lines 565017150d31
27d ago Changed 15ce7e6daad6
1mo ago Changed bf48769d7e3a
1mo ago Changed · +3 lines ddaca35bfb9d
1mo ago First seen · 105 lines scan A bcf5ef91d17f

Subscribe to this mod's changes

temper is a plugin published in the GitHub repository galando/temper (18 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Code review Testing

temper next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tempergalando/temper	Plugin	18	yesterday	MIT	A	—	Claude Code
han-communicationtestdouble/han	Plugin	337	5d ago	MIT	A	—	Claude Code
pedantic-coderoborchers/fractional-cto	Plugin	36	12d ago	MIT	A	—	Claude Code
ai-infra-auto-driven-skillsBBuf/AI-Infra-Auto-Driven-SKILLS	Plugin	1.1k	yesterday	none	A	—	Claude Code
git-prCasper-Studios/casper-marketplace	Plugin	15	7d ago	MPL-2.0	A	—	Claude Code
code-qualitydanielbodnar/skills	Plugin	2	2mo ago	MIT	A	—	Claude Code
coderabbitThrownLemon/claude-code-plugins	Plugin	2	4mo ago	MIT	A	—	Claude Code