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 skills/zxpmail/reqforge/release-buildernpx skills add zxpmail/ReqForge --skill release-buildergit clone --depth 1 https://github.com/zxpmail/ReqForgeWhat 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 | $0.00000 | $0.01873 |
| Opus 5 | $0.00000 | $0.00937 |
| Sonnet 5 | $0.00000 | $0.00375 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade B, and why
release-builder scanned grade B with 1 finding 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 2d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Build cache pollution**: `rm -rf dist &&` before final build when in doubt. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: release-builder description: Used when the user wants to package, deploy, publish, or go live, or when project development is complete and ready for delivery. Covers Web deployment, Desktop packaging, and CLI publishing, with built-in privacy audit and smoke testing. version: 1.1.0 updated: 2026-05-30 requires: []
[Task] Execute the full build-package-test-publish lifecycle according to project type. Ensure the release artifact: can be installed, can run, has no privacy leaks, has no security vulnerabilities.
[Not For] - Writing code or features -> use /dev-builder instead - Fixing bugs found during testing -> use /bug-fixer instead - Reviewing code quality -> use /code-review instead - Projects with no code yet -> use /dev-builder first
[Dependency Check] Executed on demand after requirements gathering, based on the user's chosen release channel.
Basic checks:
- Project code exists -> if no code, prompt to call /dev-builder first
- git available
- Build tools available
- package.json exists
Channel checks:
- Based on the user's chosen release channel, check the required CLI tools and authentication status for that channel
- User only wants to package (not publish) -> skip deployment tool checks
Installation strategy:
- Missing tools: the Agent autonomously determines the installation method and installs directly
- Operations requiring user login/authentication: prompt the user to complete authentication
- When user-specific assets like signing certificates are missing, explain what is needed and guide the user to prepare
Optional:
- Product-Spec.md -> if available, cross-reference features for smoke testing
- `.forge/security-guidance.md` -> if present, **read before release**
- `.forge/preflight.json` -> if present, **run `pnpm preflight`** before publish; exit code 1 = blocked (see `core/docs/external-publish-preflight.md`)
[First Principles]
Release 前必读 references/first-principles.md
[Output Style]
→ references/output-style.md(发布工程师风格)
[File Structure]
release-builder/ ├── SKILL.md ├── commands/release-builder.md └── references/ ├── first-principles.md ├── output-style.md ├── workflow.md # Step 1–8(必读) ├── release-checklist.md # 版本/构建/隐私/依赖/Git ├── release-strategy.md # Web / Desktop / CLI ├── rollback-strategy.md ├── finishing-branch-checklist.md ├── anti-rationalization.md ├── anti-ai-slop-checklist.md └── yolo-mode.md
[Gotchas]
Privacy leaks in build artifacts: Always grep for /Users/, C:\Users\, API_KEY, sk-ant- before packaging.
Skipping smoke test: Run the binary / hit homepage / verify core flow — compilation ≠ shippable.
Version tag mismatch: package.json, git tag, and artifact name must match.
Build cache pollution: rm -rf dist && before final build when in doubt.
[Anti-Rationalization Checklist]
→ references/anti-rationalization.md
遇 skipping smoke test / skipping privacy audit / skipping rollback plan 时读取。
[Output Artifacts] - Build artifacts — .next/, dist/, release/ and other build output directories - Deployment URL (Web) — production environment access address - npm package publish (CLI) — version on npm registry - Git tag — v[version] tag + GitHub Release (optional)
What ships with it
13 files beside SKILL.md 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.
- commands/release-builder.md 666 B
- references/anti-ai-slop-checklist.md 3.2 KB
- references/anti-rationalization.md 1.2 KB
- references/finishing-branch-checklist.md 723 B
- references/first-principles.md 1.3 KB
- references/output-style.md 777 B
- references/release-checklist.md 1.6 KB
- references/release-dimension-checklist.md 4.2 KB
- references/release-strategy.md 1.2 KB
- references/rollback-strategy.md 551 B
- references/workflow.md 3.2 KB
- references/yolo-mode.md 679 B
- skill.json 894 B
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.
- 2d ago First seen · 169 lines · 0 tokens per session scan B 69fcc15c8308
release-builder is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,873 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用.
orchestration-team
Operating manual for the orchestration pod. Covers lead vs peer roles, monitoring with rig commands, permission handling, implementation pair gating, dogfood loops, review routing, agent behavioral models, intervention discipline, and communication culture.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.