New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Task Backlog Initializer

by mylukin in mylukin/agent-foreman

Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.

No licenceAuto-check: notesTesting & QA

Install Agent Task Backlog Initializer

skills CLI
$ npx skills add mylukin/agent-foreman --skill init-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mylukin/agent-foreman init-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/agent-foreman/skills/init-harness .claude/skills/init-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
init-harness
GitHub stars
250
Token cost
~681 tokens
SKILL.md length
176 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
None found

At a glance

Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.

  • Works in 3 steps: ARCHITECTURE.md exists → use it (fast) → Source code exists → AI scan + auto-save… → Empty project → generate from goal
  • Setting up a feature backlog and progress tracking for a new or existing project
  • SKILL.md covers Quick Start, TDD Mode (Default: Recommended), Modes and Task Types, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Running the init command creates a feature backlog folder, a progress log, an init script, and a project guide file, detecting the project either from an existing architecture document, a scan of existing source, or a fresh starting point for an empty repo. During setup it asks for a test-discipline level — strict, where tasks can't be marked done without tests, a recommended default where tests are suggested, or disabled entirely.

It also offers a merge mode that adds new features to an existing backlog, a fresh mode that replaces every feature, and a preview mode that shows changes without writing anything, plus task types for ops, data, infrastructure, or manual-only verification work. For an existing project it suggests running an analysis pass first so the setup understands the codebase before creating any task structure.

When your agent uses it

  • Setting up a feature backlog and progress tracking for a new or existing project
  • Turning on strict test enforcement for agent-driven work
  • Previewing what a backlog setup would change before committing to it

Example prompts

  • “Initialize the task backlog with strict test enforcement for this repo.”
  • “Set up a feature backlog for this existing codebase in merge mode.”
  • “Preview what the init command would create without changing anything.”

Requirements

  • The agent-foreman CLI installed
  • Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep, Write, Edit

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. ARCHITECTURE.md exists → use it (fast)
  2. Source code exists → AI scan + auto-save ARCHITECTURE.md
  3. Empty project → generate from goal

What it can do on your machine

Read from SKILL.md and the folder at commit 2763f83. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Glob
    • Grep
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Task Backlog Initializer loads about 681 tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 176 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~681

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Glob, Grep, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 176 words (~681 tokens).

name
init-harness
allowed-tools
Bash, Read, Glob, Grep, Write, Edit
user-invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugins/agent-foreman/skills/init-harness of mylukin/agent-foreman.

Open the folder on GitHubat commit 2763f83

Compare with similar skills

Agent Task Backlog Initializer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Task Backlog Initializer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Task Backlog Initializer this skillmylukin/agent-foreman250—~681Automated safety check: NotesNone
Context Modes0xNyk/lacp305—~313Automated safety check: PassMIT
TasksRafaelGB/Obsidian-ZettelFlow174—~573Automated safety check: PassMIT
Implementericrisco/rsc-harness174—~5.9kAutomated safety check: NotesMIT
Testing Skills With Subagentsed3dai/ed3d-plugins2503 repos~3.5kAutomated safety check: PassNone
Agent Teamsalinaqi/maggy707—~5kAutomated safety check: NotesMIT

Similar skills

  • Context Modes

    0xNyk/lacp

    Structured work modes for agent sessions. An agent skill from 0xNyk/lacp.

    305 GitHub stars~313 tokensUpdated 17 days ago
    Agent WorkflowsAuto-check passed

  • Tasks

    RafaelGB/Obsidian-ZettelFlow

    Stage 3 of the SDD pipeline — turn a ZettelFlow plan (in a GitHub issue comment) into an ordered TDD task checklist posted as a second issue comment.

    174 GitHub stars~573 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Implement

    ericrisco/rsc-harness

    A skill your agent uses when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify.

    174 GitHub stars~5.9k tokensUpdated yesterday
    Testing & QAAuto-check: notes

  • Testing Skills With Subagents

    ed3dai/ed3d-plugins

    A skill your agent uses when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation…

    250 GitHub starsUsed in 3 repos~3.5k tokens
    Testing & QAAuto-check passed

  • Agent Teams

    alinaqi/maggy

    Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

    707 GitHub stars~5k tokensUpdated 15 days ago
    Testing & QAAuto-check: notes

  • Foreman Verify

    VisionForge-OU/foreman

    Headless self-verification gate a Foreman worker runs before it claims an issue is done.

    443 GitHub stars~901 tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

More from mylukin/agent-foreman

  • Feature Next Task Workflow

    mylukin/agent-foreman

    Enforces a strict next-implement-check-done cycle through the agent-foreman CLI so an agent works one backlog task at a time, with optional TDD gating.

    250 GitHub stars~927 tokensUpdated 8 mo ago
    Auto-check: notes

  • Agent-Foreman Feature Run

    mylukin/agent-foreman

    Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.

    250 GitHub stars~1.6k tokensUpdated 8 mo ago
    Auto-check: notes

  • Multi-Role Spec and Task Breakdown

    mylukin/agent-foreman

    Runs a requirement through four research-backed specialist agents, a PM, a UX designer, a tech architect and QA, to produce implementable tasks.

    250 GitHub stars~5.1k tokensUpdated 8 mo ago
    Auto-check: notes

  • Project Analyze

    mylukin/agent-foreman

    Scans codebases to generate architecture documentation (ARCHITECTURE.md). Use when joining an existing project, understanding codebase structure, exploring…

    250 GitHub stars~253 tokensUpdated 8 mo ago
    Auto-check: notes

Categories

Questions about Agent Task Backlog Initializer

What does Agent Task Backlog Initializer do?

Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command. Running the init command creates a feature backlog folder, a progress log, an init script, and a project guide file, detecting the project either from an existing architecture document, a scan of existing source, or a fresh starting point for an empty repo. During setup it asks for a test-discipline level — strict, where tasks can't be marked done without tests, a recommended default where tests are suggested, or disabled entirely.

When should I use Agent Task Backlog Initializer?

Agent Task Backlog Initializer fits situations like: setting up a feature backlog and progress tracking for a new or existing project; turning on strict test enforcement for agent-driven work; previewing what a backlog setup would change before committing to it.

How do I install Agent Task Backlog Initializer in Claude Code?

Run `npx skills add mylukin/agent-foreman --skill init-harness -a claude-code`. Or copy the skill folder (plugins/agent-foreman/skills/init-harness in mylukin/agent-foreman) into .claude/skills/init-harness in your project. Claude Code loads it when a task matches its description.

How do I install Agent Task Backlog Initializer in Codex?

Run `npx skills add mylukin/agent-foreman --skill init-harness -a codex`. Or copy the skill folder (plugins/agent-foreman/skills/init-harness in mylukin/agent-foreman) into .agents/skills/init-harness in your project. Codex loads it when a task matches its description.

Can I use Agent Task Backlog Initializer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mylukin/agent-foreman --skill init-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/init-harness, .gemini/skills/init-harness, .github/skills/init-harness and .opencode/skills/init-harness in your project.

What does Agent Task Backlog Initializer need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Task Backlog Initializer is instructions for the agent only. Our summary lists: The agent-foreman CLI installed. Its frontmatter pre-approves these tools: Bash, Read, Glob, Grep, Write, Edit.

Does Agent Task Backlog Initializer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Task Backlog Initializer safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agent Task Backlog Initializer use?

No licence was found for Agent Task Backlog Initializer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Agent Task Backlog Initializer use?

About 681 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Task Backlog Initializer?

Skills that share tags, products or a category with Agent Task Backlog Initializer: Context Modes (0xNyk/lacp, 305 stars), Tasks (RafaelGB/Obsidian-ZettelFlow, 174 stars), Implement (ericrisco/rsc-harness, 174 stars) and Testing Skills With Subagents (ed3dai/ed3d-plugins, 250 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Task Backlog Initializer?

mylukin (a GitHub user) maintains it in mylukin/agent-foreman, which has 250 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on January 23, 2026.

Source: mylukin/agent-foreman on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.