Borrowing it
Nothing to install: this file belongs to opencue/cuecards. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/opencue/cuecards/main/.agents/skills/vc-generate-plan/SKILL.mdgit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/vc-generate-plan)<a href="https://agentmods.dev/skills/opencue/cuecards/vc-generate-plan"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/vc-generate-plan.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 5.1 | $0.00040 | $0.00711 |
| Opus 5 | $0.00020 | $0.00356 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
vc:generate-plan 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Plan
Use this skill to produce the authoritative implementation plan artifact set for Flowser work.
This skill is the canonical planning contract for the repo. Planning discipline previously spread across vc:plan now belongs here plus the plan-agent prompt.
Normal output is one plan file.
For large multi-phase programs, this skill instead defines how to create an umbrella plan plus
phase-plan set under one feature folder. See process/development-protocols/phase-programs.md.
Optional input: a feature idea plus simple or complex when the user already knows the intended depth.
Workflow
- Read
references/generate-plan.mdfor the full plan contract. - Run
date +%d-%m-%ybefore choosing the filename. - If complexity is not obvious, ask whether the plan is
SIMPLEorCOMPLEX. - Save the plan to
process/general-plans/active/unless the work belongs to an existingprocess/features/{feature}/active/folder. - Read
process/context/all-context.mdwhen present to choose relevant context docs. - For complex plans, read
process/context/planning/example-complex-prd.mdbefore writing. - Include automated and manual verification gates from
process/context/tests/all-tests.md. - For new or newly touched direct
*_PLAN_*.mdplans, include explicit sections forTouchpoints,Public Contracts,Blast Radius,Verification Evidence, andResume and Execution Handoff. - Keep resume/dependency notes Markdown-structured for now; do not invent a second machine-only schema.
- If the work is a large multi-phase program, create or update a feature folder plan set:
- one umbrella/orchestration plan
- one direct plan file per phase
- one durable report destination per phase
- Validate the generated artifact:
node .Codex/skills/vc-generate-plan/scripts/validate-plan-artifact.mjs <plan-path>
Important Rules
- For standard work, create exactly one plan file.
- For a phase program, create one umbrella plan plus one direct plan file per phase.
- Prefer
process/features/{feature}/active/when the topic maps to an existing feature folder. - Keep phase status honest: code-only completion is
CODE DONE, notVERIFIED. - Make execution trust explicit inside the plan: what code or data can change, what contracts are exposed, what proof is required, and how EXECUTE should resume after compaction.
- End with the next instruction for RIPER-5 or Cursor Plan mode.
- Treat validation failures as blockers before presenting the plan as ready.
- Fold red-team questions, dependency mapping, verification gates, and ambiguity checks into the generated plan itself instead of relying on a parallel plan-owner workflow.
- Do not hide a large program inside one giant plan if execution will actually happen phase by phase.
- Preserve the older complex-plan behavior by keeping pre-phase research and proof gates inside each phase plan; the new protocol changes the artifact shape, not the rigor.
What ships with it
2 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 · 55 lines · 40 tokens per session scan A 618fcf5a7ad8
vc:generate-plan is a skill published in the GitHub repository opencue/cuecards (5 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 711 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.
loongsuite-pilot-ops
Skill "loongsuite-pilot-ops" from alibaba/loongsuite-pilot, covering loongsuite-pilot-ops, quick start, todo: add quick start commands and usage.
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…