plan-check-gate
Require fact-backed research and an explicit implementation plan before writing code. Use when the user asks for planning first, wants verification/citations, says they may be wrong, or when the task is high-risk/high-cost and code should stay blocked until plan approval.
Best use case
plan-check-gate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Require fact-backed research and an explicit implementation plan before writing code. Use when the user asks for planning first, wants verification/citations, says they may be wrong, or when the task is high-risk/high-cost and code should stay blocked until plan approval.
Teams using plan-check-gate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/plan-check-gate/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How plan-check-gate Compares
| Feature / Agent | plan-check-gate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Require fact-backed research and an explicit implementation plan before writing code. Use when the user asks for planning first, wants verification/citations, says they may be wrong, or when the task is high-risk/high-cost and code should stay blocked until plan approval.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Plan Check Gate ## Overview Enforce a pre-code quality gate. Do research first, separate verified facts from assumptions, and produce an approval-ready plan before any file edits. ## Pre-Code Workflow 1. Define scope - Restate objective, constraints, and acceptance criteria. - Identify what must be true for the task to be considered done. 2. Build fact set - Collect only relevant facts. - Mark each item as `verified` or `assumption`. 3. Research and verify - Prefer primary sources for technical claims (official docs/specs/repos/papers). - If information can change (versions, APIs, pricing, policies, benchmarks), re-check before coding. - Record source links and concrete dates. 4. Propose plan - Provide implementation steps, test plan, risks, and rollback idea. - Keep steps small and reversible. 5. Approval gate - Ask for explicit go/no-go. - Do not write code until approved. ## Output Contract Before coding, return: - `objective` - `constraints` - `verified_facts` (with sources) - `assumptions` - `plan_steps` - `test_strategy` - `risks` - `decision` (`hold` or `go`) ## Coding Unlock Conditions Only start implementation when all are true: - At least one high-signal source exists for each unstable or critical claim. - Assumptions are explicitly listed. - Plan is testable and scoped. - User approved execution. ## Resources - Checklist and prompt snippets: `references/plan-check-checklist.md` - Artifact generator: `scripts/emit_plan_check.py` Use the script to create a reusable planning record: ```powershell python scripts/emit_plan_check.py --task "your task" --out ".codex-plan-check/your-task.md" --requires-research --source "https://example.com/doc" ```
Related Skills
scbe-connector-health-check
Run safety-first connector diagnostics for MCP/services used by SCBE so outreach, research, publishing, and runtime calls do not break silently.
multi-agent-review-gate
Run a structured review gate before merging multi-agent outputs. Use when multiple agents have produced work packets that need quality checks, conflict detection, and approval before integration.
scbe-governance-gate
Evaluate the Grand Unified Governance function G(xi, i, poly) that makes ALLOW/DENY/QUARANTINE decisions based on the full 9D state, intent, and polyhedral topology. Use when implementing or modifying the governance decision pipeline, adding new constraint checks, or debugging access decisions.
scbe-gate-swap
Analyze and swap between 2-gate (binary/negabinary) and 3-gate (balanced ternary) encoding for stability optimization. Use when evaluating gate efficiency, comparing encoding strategies for governance decisions, or optimizing bit-level representation in SCBE subsystems.
scbe-email-checker
Check ProtonMail and Gmail for important emails — patent updates, revenue notifications, outreach replies, security alerts. Use when asked to "check email", "check my inbox", "any new emails", "patent email", "check proton", "check gmail", or at session start for a quick email briefing.
latticegate-orchestrator
Manages AI safety governance using 21D hyperbolic embeddings and phase tunnel gates. Invoke when analyzing agent drift, applying SCBE-AETHERMOORE protocols, packaging governance products for sale, or running the monetization pipeline.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.