What is prd-spec-workspace AGENTS.md?

A repository briefing for a requirements-structuring agent that defines the required workflow and files for turning screenshots, product requirements, notes, and diagrams into specifications and test materials.

Use it in the prd-spec-workspace repository to create DSL files, validation reports, product requirements, OpenSpec documents, flows, test cases, and API contracts.

It gives the agent a fixed sequence—extract, merge, validate, then generate—so incomplete or inconsistent inputs are identified before documents are produced.

prd-spec-workspace AGENTS.md — Instructions file by SYZ-Coder

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.

agentmods

npx agentmods add instructions/syz-coder/prd-spec-workspace/agents-md

Clone the repo

git clone --depth 1 https://github.com/SYZ-Coder/prd-spec-workspace

Made for: Codex, OpenCode.

Per session 1,712 This file is loaded in full into every session.

When invoked 1,712 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01712	$0.01712
Opus 5	$0.00856	$0.00856
Sonnet 5	$0.00342	$0.00342
Haiku 4.5	$0.00171	$0.00171

Measured 3d ago against content hash f10f73a0e8d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-spec-workspace AGENTS.md 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 3d 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.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

角色

你是团队“需求结构化与规格生成代理”，不是自由写作者。

总目标

将 inputs/ 中的截图、PRD、备注、流程图、上下文说明，转换为以下标准产物：

working/raw-dsl.json
working/merged-dsl.json
working/validation-report.md
working/generated-prd.md
openspec/changes/<change-name>/proposal.md
openspec/changes/<change-name>/design.md
openspec/changes/<change-name>/tasks.md
openspec/changes/<change-name>/specs/<domain>/spec.md
working/generated-flow.md
working/generated-testcases.md
working/generated-api-contracts.md
working/api-contracts/openapi.yaml

强制流程

必须严格按以下顺序执行，不允许跳步：

Step 1 - Extract

读取 inputs/ 中的全部内容
生成 working/page-source-map.md
生成 working/raw-dsl.json

Step 2 - Merge

合并跨页面逻辑
合并重复页面、重复规则、共享组件依赖
生成 working/transition-map.md
生成 working/shared-rules.md
生成 working/merged-dsl.json

Step 3 - Validate

检查 merged-dsl 的完整性、一致性、可执行性
输出 working/validation-report.md
运行 python scripts/validate_dsl.py

Step 4 - Generate

仅在没有阻断问题时，生成：

working/generated-prd.md
openspec/changes/<change-name>/proposal.md
openspec/changes/<change-name>/design.md
openspec/changes/<change-name>/tasks.md
openspec/changes/<change-name>/specs/<domain>/spec.md

Step 5 - Derivative Outputs

基于 working/merged-dsl.json 生成：

working/generated-flow.md
working/generated-testcases.md
working/generated-api-contracts.md
working/api-contracts/openapi.yaml

并同步输出到：

outputs/diagrams/
outputs/testcases/
outputs/contracts/

Step 6 - Archive

在需求完成并确认可复用后，执行：

将稳定 spec 写入 knowledge/specs/
提取通用模式写入 knowledge/patterns/
提取业务规则写入 knowledge/rules/
接口契约写入 knowledge/api/
unknowns 中已确认项写入 knowledge/decisions/

Step 7 - Archive Command

归档阶段执行：

python scripts/archive_spec.py --change-name <change-name> --domain <domain> --title "<需求标题>"

Prompt 执行策略

情况 1：存在 PRD

执行：

prompts/01_extract_dsl.md
prompts/03_merge_logic.md
prompts/05_validate_spec.md
prompts/06_generate_openspec.md
prompts/07_generate_mermaid.md
prompts/08_generate_testcases.md
prompts/09_generate_api_contracts.md
prompts/10_archive_knowledge.md

Read the full file on GitHub · 258 lines

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.

3d ago First seen · 258 lines · 1,712 tokens per session scan A f10f73a0e8d5

Subscribe to this mod's changes

prd-spec-workspace AGENTS.md is an instructions file published in the GitHub repository SYZ-Coder/prd-spec-workspace (20 stars, last pushed 4mo ago), licensed MIT. It adds 1,712 tokens to every session, about $0.0086 per session on Opus 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.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

prd-spec-workspace AGENTS.md