start-work

start-work is a command for Claude Code from DimitriGeelen/agentic-engineering-framework. It costs 0 tokens per session (397 once invoked), scanned A, original, Apache-2.0.

Before beginning ANY implementation work, execute this workflow. This command enforces the core principle: "Nothing gets done without a task.".

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dimitrigeelen/agentic-engineering-framework/start-work
Clone the repo
git clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-framework

Made for: Claude Code.

Wrote 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.

agentmods badge for start-work

README.md
[![agentmods](https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/start-work.svg)](https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/start-work)
Your own site
<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/start-work"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/start-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 397 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00397
Opus 5 $0.00000 $0.00198
Sonnet 5 $0.00000 $0.00079
Haiku 4.5 $0.00000 $0.00040

Measured today against content hash 7fb9d8a953a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-work 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 today.

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.

.claude/commands/start-work.md · 63 lines

What it actually says

/start-work - Task-First Gate for Agentic Engineering Framework

Before beginning ANY implementation work, execute this workflow. This command enforces the core principle: "Nothing gets done without a task."

When To Use

ALWAYS use before:

  • Implementing a feature, bugfix, or refactor
  • Following a plan
  • Executing any skill that produces code changes

Step 1: Check Context

Run in parallel:

  1. cat .context/working/focus.yaml — check if current_task is set
  2. ls .tasks/active/ — list active tasks

If current_task is already set and valid: skip to Step 3.

Step 2: Create or Resume Task

If no active task for this work:

New work:

fw work-on "DESCRIPTION" --type TYPE

Resuming known task:

fw work-on T-XXX

TYPE is one of: build, specification, design, test, refactor, decommission

Do NOT proceed to implementation until this step completes successfully.

Step 3: Confirm Gate

Verify:

  • current_task in focus.yaml is set
  • Task file exists in .tasks/active/
  • Task status is started-work

Print confirmation:

Task gate passed: T-XXX ({task_name})
Proceeding with implementation.

Step 4: Proceed

Now proceed with implementation. Optionally use /explore or /plan if the task needs it.

Rules

  • This gate takes precedence over ALL plugin skills
  • "Invoke skills BEFORE any response" means: after this gate passes
  • If a skill says "implement now" — this gate comes first
  • The PreToolUse hook will block Write/Edit without an active task anyway
  • This command exists to make the agent aware BEFORE hitting the hook
Changes

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.

  1. today First seen · 63 lines · 0 tokens per session scan A 7fb9d8a953a2

Subscribe to this mod's changes

start-work is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 397 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 2026-09-04.