work

work is a skill for Claude Code from ondrej-svec/heart-of-gold-toolkit. It costs 71 tokens per session (2,305 once invoked), scanned A, original, MIT.

A workflow for carrying an approved development plan through implementation and release. It organizes work by dependencies and includes testing, code review checks, commits, and pushing changes.

In plain words
What is it for?
Use it to implement planned features, test after changes, commit in small steps, run quality checks, and prepare or push a release.
Why use it?
It reduces skipped steps, oversized changes, late testing, and accidental releases with known problems. It requires a written plan so implementation follows agreed decisions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the marvin plugin — 13 skills, 3 agents, 2 hooks shipped together

Good fit Use it to implement planned features, test after changes, commit in small steps, run quality checks, and prepare or push a release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ondrej-svec/heart-of-gold-toolkit/work
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.

Any agent
npx skills add ondrej-svec/heart-of-gold-toolkit --skill work
Clone the repo
git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install marvin, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks.

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 work

README.md
[![agentmods](https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/work/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/work)
Your own site
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/work"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/work/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.

agentmods 80×15 button for work

Your own site · 80×15
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/work"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00071 $0.02305
Opus 5 $0.00036 $0.01153
Sonnet 5 $0.00014 $0.00461
Haiku 4.5 $0.00007 $0.00231

Measured 11d ago against content hash ac369a93c0de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 11d 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.

plugins/marvin/skills/work/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work

Execute a plan and ship it. This is the ONLY skill that writes code. Read tasks, implement in dependency order, test after every change, commit incrementally, quality checks, push.

Boundaries

This skill MAY: read code, write code, edit files, run tests, run linters, commit, push, create PRs. This skill MAY NOT: skip the plan, skip tests, ship with known failures, commit .env or secrets.

This skill requires a plan. If no plan exists, suggest /deep-thought:plan first. Don't improvise implementation from scratch.

Common Rationalizations

Shortcut Why It Fails The Cost
"Skip reading the plan — I'll figure it out" The plan has context, decisions, and dependencies you'll miss Build the wrong thing → rework
"Giant commits — I'll sort it out later" Hard to review, hard to revert, hide bugs Technical debt + review burden
"Tests at the end — I'm in flow" Late testing finds problems when fixing them is most expensive Cascading failures
"Ship without quality checks — small change" Small changes touch auth, data, or boundaries more often than you think Bug in production from a "safe" change

Phase 0: Load the Plan

Entry: User invoked /work with a plan path or no arguments.

If invoked with a plan path:

  1. Read the plan completely
  2. Identify: tasks (checkboxes), dependencies, acceptance criteria

If invoked without a path:

  • Check docs/plans/ (or project override path) for the most recent active plan (status: approved or status: in_progress in frontmatter)
  • If one found: Ask the user whether to start that plan or choose a different one.
  • If multiple found: Ask the user which plan to use.
  • If none found: Ask whether to create a /deep-thought:plan first or describe what to build.

Prefer the harness's structured choice UI when available. Otherwise present concise numbered options in plain text.

If anything in the plan is unclear: Ask clarifying questions now — better to ask than build wrong.

Read the full file on GitHub · 264 lines

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. 11d ago First seen · 264 lines · 71 tokens per session scan A ac369a93c0de

Subscribe to this mod's changes

work is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 21d ago), licensed MIT. It adds 71 tokens to every session and 2,305 once invoked, about $0.0004 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.