Borrowing it
Nothing to install: this file belongs to opensesh/karimo-overview. 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/opensesh/karimo-overview/main/.claude/skills/writing-plans/SKILL.mdgit clone --depth 1 https://github.com/opensesh/karimo-overviewWrote 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/opensesh/karimo-overview/writing-plans)<a href="https://agentmods.dev/skills/opensesh/karimo-overview/writing-plans"><img src="https://agentmods.dev/badge/skills/opensesh/karimo-overview/writing-plans/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/opensesh/karimo-overview/writing-plans"><img src="https://agentmods.dev/badge/skills/opensesh/karimo-overview/writing-plans.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01421 |
| Opus 5 | $0.00000 | $0.00711 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
writing-plans 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 6d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
This skill activates when the user requests implementation planning, architecture design, feature roadmaps, or asks to "plan", "design", or "architect" a solution. Also activates when starting complex multi-file changes.
Core Philosophy
Write comprehensive implementation plans assuming the reader has zero context for our codebase but deep development expertise. Plans should enable any skilled developer—or parallel agent—to execute independently with zero additional guidance.
BOS Integration: Every plan must account for our design system, component patterns, and brand voice requirements at the architecture level.
Plan Structure (Required Sections)
1. Header Block
# Implementation Plan: [Feature Name]
**Goal**: [One-sentence outcome statement]
**Architecture**: [High-level approach]
**Tech Stack**: Next.js 16+, React 19, TypeScript strict, Tailwind CSS, React Aria
**Design System**: BOS-3.0 (Charcoal/Vanilla/Aperol palette, semantic tokens)
**Created**: YYYY-MM-DD
2. Design System Checklist
Before any UI task, verify:
- Components use semantic CSS variables (
--bg-primary,--fg-secondary, etc.) - Borders follow 40% opacity pattern (
border-border-secondary) - Brand color (Aperol) reserved for CTAs/active states only
- Interactive elements use React Aria Components
- Warm neutrals (Charcoal/Vanilla) instead of pure black/white
3. Task Breakdown
Each task represents 2-5 minutes of work. Use this granularity:
### Task 1: Create component skeleton
**File**: `components/feature/FeatureName.tsx`
**Type**: Component (React Aria base)
**Design Token Requirements**:
- Background: `bg-bg-secondary`
- Border: `border-border-secondary`
- Text: `text-fg-primary`
**Steps**:
1. Write failing test in `__tests__/FeatureName.test.tsx`
2. Verify test fails (RED)
3. Implement minimal component
4. Verify test passes (GREEN)
5. Commit: `feat(feature): add FeatureName component skeleton`
**Code**:
\`\`\`tsx
// **tests**/FeatureName.test.tsx
import { render, screen } from '@testing-library/react';
import { FeatureName } from '../FeatureName';
describe('FeatureName', () => {
it('renders with BOS design tokens', () => {
render(<FeatureName />);
// Verify semantic token usage
expect(screen.getByRole('region')).toHaveClass('bg-bg-secondary');
});
});
\`\`\`
**Expected Output**:
\`\`\`
FAIL **tests**/FeatureName.test.tsx
FeatureName
✕ renders with BOS design tokens (5ms)
\`\`\`
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.
- 6d ago First seen · 207 lines · 0 tokens per session scan A b21077de783c
writing-plans is a skill published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,421 tokens. 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
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
github-operations
A tool for managing GitHub pull requests and issues. Pull requests are proposed code changes for review, while issues are GitHub's way to track bugs, tasks, and questions.
team-coordination
Use before deciding how you should organize team work: DAG vs Loop, dependency shape, task waves, quality gates, acceptance criteria, interruption, replanning, or what to do after Worker results arrive. Always use this skill for team organization strategy before you call project-management or task-management.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
task-coordination
Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.
teamharness-task-execution
Use when a Worker receives TASKASSIGNED, acknowledges the task, works inside shared/tasks/{task-id}/, submits with taskflow submittask, publishes deliverables through submittask, and reports TASKCOMPLETED or blockers in the Task room.