Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/andreaswasita/copilot-agents-dojo/plan-before-codenpx skills add andreaswasita/copilot-agents-dojo --skill plan-before-codegit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/andreaswasita/copilot-agents-dojo/plan-before-code)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/plan-before-code"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/plan-before-code.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 | $0.00012 | $0.01312 |
| Opus 5 | $0.00006 | $0.00656 |
| Sonnet 5 | $0.00002 | $0.00262 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade A, and why
plan-before-code 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Before Code Skill
Forces an explicit written plan in tasks/todo.md before the agent edits any file for non-trivial work. Does NOT apply to one-line fixes, typo corrections, or any task the agent can finish in a single edit — over-planning trivial work is its own failure mode.
When to Use
- Any task that will touch 3+ files or require 3+ steps.
- Before implementing unfamiliar features or architectural changes.
- After a previous approach failed and a re-plan is needed.
- When scope or requirements are ambiguous.
- Before refactoring that crosses module boundaries.
- NOT for: typos, comment-only edits, single-line bug fixes, formatting.
Prerequisites
- A writable
tasks/todo.md(created byscripts/init.shif missing). - An approved problem statement from the user or
brainstormingskill. - The repo cloned and the working tree clean enough to start (use
powershellwithgit status).
How to Run
0. Recall prior memory for the topic (memory_recall MCP tool or scripts/memory-recall.sh) and fold it into Context.
1. Assess complexity (the 4 questions in Procedure §1).
2. If non-trivial → write plan to tasks/todo.md using the canonical block.
3. Validate the plan against the gap checklist.
4. Execute one step at a time, checking items off as you go.
Quick Reference
| Situation | Action | Tool |
|---|---|---|
| Before writing a plan | Recall prior memory | memory_recall MCP tool, or powershell → scripts/memory-recall.sh |
| Touch ≥3 files | Enter plan mode | view tasks/todo.md then edit |
| Re-plan after wall hit | Append a ## Revision N block |
edit tasks/todo.md |
| Check existing plan | Read current state | view tasks/todo.md |
| Mark step done | Flip - [ ] to - [x] |
edit tasks/todo.md |
| Resume across sessions | Re-read the plan first | view tasks/todo.md |
Procedure
Step 0: Recall Prior Memory
Before assessing complexity, surface what the dojo already knows so the plan
compounds past knowledge instead of re-deriving it. Use the memory_recall MCP
tool with the work's topic (and language/fileType when known). If that tool
is unavailable, use powershell to run scripts/memory-recall.sh --topic "<topic>".
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.
- 4d ago First seen · 133 lines · 12 tokens per session scan A 7fd1c558d34d
plan-before-code is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,312 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
database-specialist
Data-pipeline implementation specialist — change-tracker/data-loader configurations, stored procedure integration, MongoDB repository code, DI registration, and Squadron-based database tests. Triggers: SqlChangeTracker, SqlDataLoader, SqlExecutionContext, IMongoCollection, MongoConventions, DomainEntityRepository…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
prompt-creator
Expert guide for crafting high-quality, production-grade prompts and system prompts for LLMs. Use when a user wants to create, improve, debug, or evaluate a prompt — whether for Claude, GPT, or any other LLM. Triggers on create prompt, write prompt, improve prompt, system prompt, prompt engineering, prompt template…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
backend-developer
Use this skill when working on backend microservices — implementing GraphQL APIs with HotChocolate, writing MassTransit consumers/publishers, building MongoDB data access layers, configuring service startup, integrating data pipelines, or adding observability with OpenTelemetry. Triggers on: GraphQL resolvers…
email-template-developer
Use this skill when working on email, SMS, or push notification templates — authoring Handlebars HTML email templates, understanding the backend template engine, visual testing with Playwright, or managing multi-tenant template deployment. Triggers on: body.hbs.html, subject.hbs.txt, Handlebars email templates…