Context Engineering Template is a repository of instructions, examples, workflows, and validation practices that give AI coding assistants the information they need to complete software tasks. It is for developers working with Claude Code or other coding assistants, and the catalogue entries package parts of its workflow as commands, agents, instructions, and a skill.
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.
git clone --depth 1 https://github.com/coleam00/context-engineering-introWrote 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/commands/coleam00/context-engineering-intro/execute-plan)<a href="https://agentmods.dev/commands/coleam00/context-engineering-intro/execute-plan"><img src="https://agentmods.dev/badge/commands/coleam00/context-engineering-intro/execute-plan/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/commands/coleam00/context-engineering-intro/execute-plan"><img src="https://agentmods.dev/badge/commands/coleam00/context-engineering-intro/execute-plan.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 | $0.00011 | $0.01201 |
| Opus 5.5 | $0.00004 | $0.00480 |
| Sonnet 5.5 | $0.00002 | $0.00240 |
| Haiku 4.5 | $0.00001 | $0.00120 |
Grade A, and why
execute-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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Development Plan with Archon Task Management
You are about to execute a comprehensive development plan with integrated Archon task management. This workflow ensures systematic task tracking and implementation throughout the entire development process.
Critical Requirements
MANDATORY: Throughout the ENTIRE execution of this plan, you MUST maintain continuous usage of Archon for task management. DO NOT drop or skip Archon integration at any point. Every task from the plan must be tracked in Archon from creation to completion.
Step 1: Read and Parse the Plan
Read the plan file specified in: $ARGUMENTS
The plan file will contain:
- A list of tasks to implement
- References to existing codebase components and integration points
- Context about where to look in the codebase for implementation
Step 2: Project Setup in Archon
-
Check if a project ID is specified in CLAUDE.md for this feature
- Look for any Archon project references in CLAUDE.md
- If found, use that project ID
-
If no project exists:
- Create a new project in Archon using
mcp__archon__manage_project - Use a descriptive title based on the plan's objectives
- Store the project ID for use throughout execution
- Create a new project in Archon using
Step 3: Create All Tasks in Archon
For EACH task identified in the plan:
- Create a corresponding task in Archon using
mcp__archon__manage_task("create", ...) - Set initial status as "todo"
- Include detailed descriptions from the plan
- Maintain the task order/priority from the plan
IMPORTANT: Create ALL tasks in Archon upfront before starting implementation. This ensures complete visibility of the work scope.
Step 4: Codebase Analysis
Before implementation begins:
- Analyze ALL integration points mentioned in the plan
- Use Grep and Glob tools to:
- Understand existing code patterns
- Identify where changes need to be made
- Find similar implementations for reference
- Read all referenced files and components
- Build a comprehensive understanding of the codebase context
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.
- 1mo ago First seen · 139 lines · 11 tokens per session scan A e3bf3a24676e
execute-plan is a command published in the GitHub repository coleam00/context-engineering-intro (13,880 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 1,201 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.