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/request-dispatchernpx skills add zxpmail/ReqForge --skill request-dispatchergit clone --depth 1 https://github.com/zxpmail/ReqForgeWrote 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/skills/zxpmail/reqforge/request-dispatcher)<a href="https://agentmods.dev/skills/zxpmail/reqforge/request-dispatcher"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/request-dispatcher.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 | $0.00000 | $0.02134 |
| Opus 5 | $0.00000 | $0.01067 |
| Sonnet 5 | $0.00000 | $0.00427 |
| Haiku 4.5 | $0.00000 | $0.00213 |
Grade A, and why
request-dispatcher 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: request-dispatcher description: Used when the user's request is ambiguous and doesn't clearly match a single Skill's trigger criteria. Analyzes intent + project state to route to the correct Skill. Not a replacement for CLAUDE.md Skill Dispatch rules — only for edge cases where dispatch is uncertain. version: 1.0.0 updated: 2026-05-26 requires: []
[Task] Analyze ambiguous user requests and route them to the correct ReqForge Skill. When the main Agent's static dispatch rules (from CLAUDE.md [Skill Dispatch]) cannot uniquely determine the target Skill, this Skill provides a structured decision framework: classify intent → cross-reference project state → disambiguate → recommend Skill.
[Not For] - Clear-cut requests that match a single Skill trigger -> use the target Skill directly - Writing code -> use /dev-builder instead - Bug fixing -> use /bug-fixer instead - Requirements gathering -> use /product-spec-builder instead
[Dependency Check] Required: - User's natural language request -> the ambiguous message text - Project state awareness -> which artifacts exist (Product-Spec.md, DEV-PLAN.md, code, active changes/)
Optional:
- git log -> recent changes for context
- memory/ files -> known pitfalls and recent task history
[First Principles]
→ references/first-principles.md
核心:Minimum Dispatch / State Before Intent / Ask Don't Guess。
[Output Style]
→ references/output-style.md
Tone: neutral, analytical, decisive. One recommendation, not a menu.
[File Structure]
request-dispatcher/ ├── SKILL.md └── references/ ├── first-principles.md ├── output-style.md ├── workflow.md ├── dimension-checklist.md └── anti-rationalization.md
[Output Artifacts] - Dispatch recommendation (screen output) — one-line Skill name + one-sentence justification
[Dispatch Dimension Checklist] Before recommending a Skill, verify:
| Dimension | Must-Have | Recommended |
|-----------|-----------|-------------|
| **Intent Match** | User's message maps to a Skill's trigger description in CLAUDE.md | User's message is NOT already covered by a static rule (would be unnecessary dispatch) |
| **Prerequisite Check** | Target Skill's Dependency Check would pass | Target Skill's Not For section doesn't exclude the request |
| **Project State** | Required artifacts exist for the target Skill | No active changes/ folder conflict |
| **Ambiguity Resolved** | Recommendation resolves the ambiguity | User would not be surprised by the routing |
[Dispatch Decision Strategy]
| User says... | Product-Spec.md exists? | Active changes/? | Code exists? | Route to |
|---|---|---|---|---|
| "I have an idea / build something" | No | — | — | /product-spec-builder |
| "Add a feature / change something" | Yes | No | — | /change-manager propose |
| "Add a feature / change something" | Yes | Yes | — | /change-manager (resume active) |
| "This is broken / error / bug" | — | — | Yes | /bug-fixer |
| "Review / check quality" | Yes | — | Yes | /code-review |
| "Plan / how to build" | Yes | — | — | /dev-planner |
| "Build / implement / code" | Yes | — | No | /dev-builder |
| "Build / implement more" | Yes | — | Yes | /dev-builder |
| "Design / make it look good" | Yes | — | — | /design-brief-builder → /design-maker |
| "Release / deploy / ship" | — | — | Yes | /release-builder |
| "Grill me / stress-test plan / 烤问" | — | — | — | /product-spec-builder → Light Grill Mode |
| "Zoom out / explain this module" | — | — | Yes | /dev-builder → [Zoom-Out Pass] (read-only) |
| "Architecture health / ball of mud" | — | — | Yes | /dev-planner → architecture-health-pass |
| "Break into GitHub issues" | Yes | — | — | /dev-planner → optional issue slices (after plan confirm) |
| "forge-smoke failed / adapter drift / gate red" (in ReqForge repo) | — | — | — | /reqforge-greenkeeper |
What ships with it
7 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.
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 · 157 lines · 0 tokens per session scan A 0e03b746ad74
request-dispatcher is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,134 tokens. 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.
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.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
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.