Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Planning Rules

ASecurity

Planning + verification discipline for multi-phase work — code-graph-validation (incremental per-task + phase-boundary + pre-push sweeps), ADR template (MADR / Nygard format), runbook template (canonical incident-response structure). Invoke when writing or reviewing a plan, an ADR or a runbook, and before acting on the detail of plan-completion-before-push.md.

12 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsnodegitdocumentation

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add Nmor/the-claude-council --skill planning-rules --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Planning Rules?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Planning Rules
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nmor-planning-rules/badge)](https://www.skillsdirectory.com/skills/nmor-planning-rules)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: planning-rules
description: Planning + verification discipline for multi-phase work — code-graph-validation (incremental per-task + phase-boundary + pre-push sweeps), ADR template (MADR / Nygard format), runbook template (canonical incident-response structure). Invoke when writing or reviewing a plan, an ADR or a runbook, and before acting on the detail of plan-completion-before-push.md.
---

# planning-rules

> **Size budget: 25 KB.** Check: wc -c. Gate: node ~/.claude/scripts/token-budget.mjs --check
>
> Migrated 2026-06-02 from `~/.claude/rules/common/` as part of the lazy-rules-loading plan. Phase H
> will delete the source files to close the eager-load loop.

## Purpose

Planning + verification discipline for multi-phase work. This file is a ROUTING
TABLE: it names each topic and the reference file that carries its full text.
Read the row that matches the work in hand, then open that reference — the
detail is unabridged there, not summarised here.

Progressive disclosure, per `no-bloat.md` rule 10: this skill is `paths:`-gated,
so whenever a glob matches, whatever lives in this file is added to the always-on
Floor in full. The routing table is what every match pays; the references are
what only the relevant task pays.

## Standards Cited

The documentation formats the migrated rules build on; detail lives in the references.

- **Nygard, "Documenting Architecture Decisions" (2011)**: the ADR format (`references/adr-template.md`)
- **MADR (Markdown Any Decision Records)**: the ADR structure these templates stay compatible with
- **C4 Model** (Simon Brown): context, container, component and code views
- **arc42**: the architecture-documentation template the ADR rule cross-references

## Routing table

| Topic | When you need it | Reference |
| --- | --- | --- |
| **Code-graph validation** | Any task, todo, commit, phase or completion claim that touches code, config or wiring. Incremental per-task checks, the per-surface + per-language command matrices, phase-boundary sweep, pre-push full-graph gate, `BUG(unwired-…)` discipline. | [`references/code-graph-validation.md`](references/code-graph-validation.md) |
| **ADR template** | Recording a non-trivial architectural decision before the implementation lands. What counts as architectural, the MADR-compatible structure, numbering / immutability / supersede rules, standards cited. | [`references/adr-template.md`](references/adr-template.md) |
| **Runbook template** | Introducing an alert, a failure mode or an error code. The required entry structure (What you'll see → Diagnose → Fix → Verify → Communicate), the eight hard rules, the canonical incident classes. | [`references/runbook-template.md`](references/runbook-template.md) |
| **Plan completion before push** | Any `git push`, `git push --tags`, or `gh pr create` during plan execution. Commit policy per plan, the push gate, the narrow bug-fix exception, branch protection, the AI-attribution trailer ban, the canonical push flow. | [`references/plan-completion-before-push.md`](references/plan-completion-before-push.md) |

## Source files migrated

- `rules-library/common/code-graph-validation.md`
- `rules-library/common/adr-template.md`
- `rules-library/common/runbook-template.md`

Attribution

NmorNmor
View sourceMore from Nmor →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →