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.
npx agentmods add agents/eight-acres-lab/openmelon/speckit.specifygit clone --depth 1 https://github.com/eight-acres-lab/openmelonWrote 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/agents/eight-acres-lab/openmelon/speckit.specify)<a href="https://agentmods.dev/agents/eight-acres-lab/openmelon/speckit.specify"><img src="https://agentmods.dev/badge/agents/eight-acres-lab/openmelon/speckit.specify.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.03415 |
| Opus 5 | $0.00006 | $0.01707 |
| Sonnet 5 | $0.00003 | $0.00683 |
| Haiku 4.5 | $0.00001 | $0.00342 |
Grade A, and why
speckit.specify 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.
This is a copy
92% identical to speckit.specify — 73 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Pre-Execution Checks
Check for extension hooks (before specification):
- Check if
.specify/extensions.ymlexists in the project root. - If it exists, read it and look for entries under the
hooks.before_specifykey - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter out hooks where
enabledis explicitlyfalse. Treat hooks without anenabledfield as enabled by default. - For each remaining hook, do not attempt to interpret or evaluate hook
conditionexpressions:- If the hook has no
conditionfield, or it is null/empty, treat the hook as executable - If the hook defines a non-empty
condition, skip the hook and leave condition evaluation to the HookExecutor implementation
- If the hook has no
- For each executable hook, output the following based on its
optionalflag:- Optional hook (
optional: true):## Extension Hooks **Optional Pre-Hook**: {extension} Command: `/{command}` Description: {description} Prompt: {prompt} To execute: `/{command}` - Mandatory hook (
optional: false):## Extension Hooks **Automatic Pre-Hook**: {extension} Executing: `/{command}` EXECUTE_COMMAND: {command} Wait for the result of the hook command before proceeding to the Outline.
- Optional hook (
- If no hooks are registered or
.specify/extensions.ymldoes not exist, skip silently
Outline
The text the user typed after /speckit.specify in the triggering message is the feature description. Assume you always have it available in this conversation even if $ARGUMENTS appears literally below. Do not ask the user to repeat it unless they provided an empty command.
Given that feature description, do this:
- Generate a concise short name (2-4 words) for the branch:
- Analyze the feature description and extract the most meaningful keywords
- Create a 2-4 word short name that captures the essence of the feature
- Use action-noun format when possible (e.g., "add-user-auth", "fix-payment-bug")
- Preserve technical terms and acronyms (OAuth2, API, JWT, etc.)
- Keep it concise but descriptive enough to understand the feature at a glance
- Examples:
- "I want to add user authentication" → "user-auth"
- "Implement OAuth2 integration for the API" → "oauth2-api-integration"
- "Create a dashboard for analytics" → "analytics-dashboard"
- "Fix payment processing timeout bug" → "fix-payment-timeout"
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 First seen · 307 lines · 13 tokens per session scan A 4fe230f26eb6
speckit.specify is an agent published in the GitHub repository eight-acres-lab/openmelon (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 3,415 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to speckit.specify, differing in 73 lines, and is treated as a copy.
Other agents, from other repositories
reviewer-test-coverage
Review code changes for missing tests, untested edge cases, and test quality.
reviewer-code-quality
Review code changes for bugs, logic errors, edge cases, and code smells.
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
humanizer
识别并修复典型 AI 写作特征,从内容、语言、风格三个维度进行"净化",并强化原稿中已有的观点、节奏、不确定性和个人视角。Humanizer 只改表达,不创造事实、经历或证据。包含严格的黑名单过滤和 50 分制质量自评。.
wechat-reader-test
多平台读者压力测试器(保留 wechat-reader-test 名称以兼容既有工作流)。 从 01theme.md 读取发布平台,为公众号、今日头条、知乎选择不同的定性测试矩阵; 不伪造 CTR、完读率或推荐量预测。由工作流导演在 Stage 9 显式调用。.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.