Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zxpmail/ReqForgenpx agentmods add skills/zxpmail/reqforge/dev-plannerWrote 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/dev-planner)<a href="https://agentmods.dev/skills/zxpmail/reqforge/dev-planner"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/dev-planner/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.
<a href="https://agentmods.dev/skills/zxpmail/reqforge/dev-planner"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/dev-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 1 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 5.1 | $0.00000 | $0.02224 |
| Opus 5.5 | $0.00000 | $0.00890 |
| Sonnet 5.5 | $0.00000 | $0.00445 |
| Haiku 4.5 | $0.00000 | $0.00222 |
Grade A, and why
dev-planner 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: dev-planner description: Used when Product-Spec.md is complete and needs to be planned into development phases. Also used to update existing development plans after Spec changes. Outputs DEV-PLAN.md. version: 1.1.0 updated: 2026-05-26 requires: []
[Task] Generation Mode: Read Product-Spec.md (and Design-Brief.md, if present), analyze feature dependency relationships, WebSearch to validate technology choices, output a phased development plan DEV-PLAN.md.
**Iteration Mode**: When the Product Spec changes, analyze the scope of impact, update the Phase breakdown and file inventory in DEV-PLAN.md. Completed Phases (marked with [x]) remain untouched.
[Not For] - Writing actual code -> use /dev-builder instead - Gathering requirements -> use /product-spec-builder instead - Fixing bugs -> use /bug-fixer instead
[Dependency Check] Executed automatically as the first step when the Skill starts:
Required:
- Product-Spec.md -> if missing, prompt user to call /product-spec-builder first
- Product-Spec.md must include completed **§ Idea Stage Exit Criteria** (three questions) — if missing or `TBD`, route back to `/product-spec-builder` before generating DEV-PLAN
Optional (degradation mode):
- Design-Brief.md -> if missing, mark as "no design specification mode", visual details annotated as [TBD by Design Brief]
- Design tool MCP -> if not connected or no files, rely only on text descriptions, mark as "no design draft mode"
- Existing project code -> if present, scan existing structure as constraints, enter iteration mode
[First Principles]
Plan 前必读 references/first-principles.md
Tech Stack: 规划前读 .forge/dev-map.md 的技术栈节，确保 DEV-PLAN.md 的技术栈与 dev-map 一致。
[Shared Discipline]
Karpathy 四原则 → ../_shared/karpathy-discipline.md
[HARD-GATE]
Until DEV-PLAN.md saved and user explicitly confirms → write .forge/plan-confirmed.json → MUST NOT invoke /dev-builder. Chat "looks good" ≠ confirm.
Prerequisites: Product-Spec.md must exist. Rationalizations → references/plan-hard-gate-rationalization.md
[File Structure]
dev-planner/ ├── SKILL.md ├── commands/dev-planner.md └── references/ ├── first-principles.md ├── analysis-dimension-checklist.md ├── analysis-strategies.md ├── workflow.md ├── architecture-health-pass.md └── plan-hard-gate-rationalization.md ../_shared/
[Output Style]
→ ../_shared/output-style-concise.md（Plan 额外要求：每 Phase 可独立编译运行；Task 列具体文件路径；禁止 TBD）
→ DEV-PLAN 完成必须附加 ../_shared/output-status-protocol.md
[Gotchas]
Unrealistic Phasing: Each Phase must produce compilable, runnable output — split if no visible outcome.
Missing dependency order: infrastructure → data → API → UI.
Tech stack without WebSearch: Confirm versions before writing DEV-PLAN.
Ignoring existing code: Iteration mode — scan structure first.
Missing MVP Scope: Fill ## MVP Scope before Phase 1.
[Output Artifacts]
- DEV-PLAN.md — Phased development plan (created in generation mode, updated in iteration mode)
- changes/<change-name>/tasks.md — Task breakdown (filled when /change-manager apply invokes dev-planner for that change only — not by product-spec-builder iteration)
- .forge/content-verify.json — (optional, recommended) forge-verify contract base generated from Phase requirements. Produced by Step 6 of Output Phase when user confirms plan. See references/generate-contracts.md.
What ships with it
11 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/dev-planner.md 503 B
- references/analysis-dimension-checklist.md 3.2 KB
- references/analysis-strategies.md 4.5 KB
- references/architecture-health-pass.md 1.3 KB
- references/first-principles.md 3.7 KB
- references/generate-contracts.md 3.6 KB
- references/plan-critique-check.md 5.0 KB
- references/plan-hard-gate-rationalization.md 866 B
- references/workflow.md 13 KB
- skill.json 936 B
- templates/dev-plan-template.md 9.3 KB
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.
- 1mo ago First seen · 167 lines · 0 tokens per session scan A 8896421c88b4
dev-planner is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,224 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-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
oma-hwp
Convert Hangul HWP, HWPX, or HWPML documents to Markdown with kordoc. Use for text, table, and image extraction from these formats.