optim-agent/dsh-plans/reference-before-plan
Claude Code and agent skill by optim-agent/dsh-plans
- community
Checking that the SKILL.md file is still in the repository.
Research references before creating a dsh-plans plan. Use when repo-change planning needs downloaded projects, articles, papers, docs, per-reference analysis, adoption questions, language settings, and reviewer or criticizer subagents; exclude direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.
Install
npx vskill@latest install optim-agent/dsh-plans/reference-before-planSKILL.md
Reference Before Plan
Use this skill when external references must shape the plan before implementation.
DSH Setup
Read ../references/dsh-planning-workflow.md and ../references/state-and-config.md — both normative — and follow their setup, state, language, and reviewer/criticizer/executor rules. State lives in dsh-plans/.state/ via ../scripts/dsh_plans_state.py init --workdir <target-workdir>; spawn reviewer and criticizer roles with the run_plan_subagent tool.
Required Reference Flow
- Inspect the target Git repo read-only before external research so search terms match the actual codebase and constraints.
- Create the
dsh-plans/.staterun state and planning artifact directory once the topic is clear. - Search proactively for related projects, articles, papers, docs, and prior art. Prefer the
web_searchtool; use tools such asghonly when already available. - Download or clone at least 3 credible references before writing
PLAN_v1.md; store large downloads outside the target repo under~/.cache/dsh-plans/refs/<repo-slug>/<topic>/. Landing pages, README-only snapshots, abstracts, package metadata, or curl-only fragments do not count when deeper source material is available. - For every reference, record source metadata and local path in
REF_ANALYSIS.mdanddsh-plans/.state/runs/<run-id>/refs.jsonl: title, URL, kind, retrieval method, date accessed, local path, coverage, and evidence gaps. - For every reference, produce a structured analysis artifact before asking adoption questions. If a code-graph tool the workspace already uses is available, generate its JSON beside the local reference and record the path. If none is available, do a manual structured read and record the waiver in
REF_ANALYSIS.md. - For every reference after analysis, ask at least 3 ref-specific adoption questions before using its ideas in
PLAN_v1.md; each based on downloaded content, recommended option first,Othersecond-last,Auto-completelast. - Block rather than pad if fewer than 3 credible references exist, unless the user explicitly narrows the topic or waives the minimum.
Auto-completecannot grant this waiver. - Continue with big-plan depth: at least 10 planning questions, required web research during brainstorming and refinement, no refinement limit, at most five high-priority comments or questions per refinement round.
REF_ANALYSIS.md
Include: original request and repo evidence that shaped the search; attempted queries and selection criteria; references selected and rejected; local download paths; structured analysis or graph JSON paths; adoption questions and recorded answers; accepted ideas, rejected ideas, and reasons; evidence gaps and user-granted waivers; language, reviewer, criticizer, and executor settings used.
Reference ideas are not eligible for PLAN_v1.md until their adoption question answers are recorded.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/reference-before-plan/SKILL.md
Popularity
- Repository stars
- 78
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/optim-agent/dsh-plans/reference-before-plan)