reference-before-plan
Research references before creating a Prime Agent 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.
npx skills add Optim-Agent/optim-plans --skill reference-before-plan --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Reference Before Plan Use this skill when external references must shape the plan before implementation. ## Setup 1. Read `../_shared/references/prime-planning-workflow.md`, `../_shared/references/state-and-config.md`, and `../_shared/references/plan-artifact-template.md`. 2. Initialize state with `python3 scripts/optim_plans.py init --repo <target-repo> --topic <topic> --plan-level reference-before-plan --request-text <original-request>`. 3. Use `.git/optim-plans` for controller state and `docs/optim-plans/YYYY-MM-DD-topic/` for public artifacts. ## Required Reference Flow 1. Inspect the target Git repo read-only before external research so search terms match the actual codebase. 2. Search proactively for related projects, articles, papers, docs, and prior art. 3. Download or clone at least 3 credible references before writing `PLAN_v1.md`. Store large downloads outside the target repo by default under `~/.cache/optim-plans/refs/<repo-slug>/<topic>/`. 4. Record source metadata with `record-reference`: title, URL, kind, retrieval method, access date, local path, coverage, and evidence gaps. 5. For every reference, produce a structured analysis artifact and record it with `record-
- Setup
- Required Reference Flow
- REFANALYSIS.md
What does the reference-before-plan skill do?
Research references before creating a Prime Agent 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.
How do I install it?
Run `npx skills add Optim-Agent/optim-plans --skill reference-before-plan --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Optim-Agent/optim-plans, a repository with 288 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.