Spec-Driven Development v2
LichAmnesia/lich-skills
Organizes long-running agent work into a Project, Sprint and Task hierarchy with per-task state files, isolated worktrees, review loops and script-checked rules.
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.
Install Agent-Foreman Feature Run
$ npx skills add mylukin/agent-foreman --skill feature-run -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mylukin/agent-foreman feature-run --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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/feature-run .claude/skills/feature-run && rm -rf skills-srcUse ~/.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/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .claude/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-runType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mylukin/agent-foreman --skill feature-run -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mylukin/agent-foreman feature-run --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/agent-foreman/skills/feature-run .agents/skills/feature-run && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .agents/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mylukin/agent-foreman --skill feature-run -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mylukin/agent-foreman feature-run --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/agent-foreman/skills/feature-run .cursor/skills/feature-run && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .cursor/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mylukin/agent-foreman.git --path plugins/agent-foreman/skills/feature-run--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mylukin/agent-foreman --skill feature-run -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mylukin/agent-foreman feature-run --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/agent-foreman/skills/feature-run .gemini/skills/feature-run && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .gemini/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mylukin/agent-foreman feature-runInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mylukin/agent-foreman --skill feature-run -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/agent-foreman/skills/feature-run .github/skills/feature-run && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .github/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mylukin/agent-foreman --skill feature-run -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mylukin/agent-foreman feature-run --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mylukin/agent-foreman.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/agent-foreman/skills/feature-run .opencode/skills/feature-run && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "feature-run" agent skill from https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run into .opencode/skills/feature-run/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-run", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
feature-run- GitHub stars
- 250
- Token cost
- ~1.6k tokens
- SKILL.md length
- 586 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- None found
At a glance
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.
- Works in 3 steps: needs_review → may be broken (highest) → failing → not implemented → Lower priority number → higher priority…
- Working through an entire backlog of pending agent-foreman tasks without supervision
- SKILL.md covers ⚠️ STRICT WORKFLOW - NO…, ⛔ CLI-ONLY ENFORCEMENT, Mode Detection and Single Task Mode, plus 9 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Every task must follow the same sequence: `agent-foreman next` to pick it, implementation, `agent-foreman check`, then `done`. Skipping or reordering steps is forbidden. Workflow decisions go through the CLI only, so the agent must not read `ai/tasks/index.json` or task files to choose a task or check status, and must not edit task files by hand to change status. Implementation is delegated to an `agent-foreman:implementer` subagent, which also handles test-driven development internally.
With a task ID, such as `auth.login`, the agent works on that task alone and stops. Without one it enters unattended mode, looping until every pending task is done, asking no questions and not stopping for errors. Tasks needing review come first, then failing ones, then lower priority numbers, with zero highest. Other rules are one task at a time, never editing acceptance criteria, and never killing running processes. Status is shown only at the start and end of a run.
When your agent uses it
- Working through an entire backlog of pending agent-foreman tasks without supervision
- Completing one named task through the next, implement, check and done cycle
- Keeping an agent from stopping with half-built features
Example prompts
- “Run all tasks in unattended mode.”
- “feature-run auth.login”
- “Complete the pending features in the backlog and report the final status.”
Requirements
- The `agent-foreman` CLI and plugin agents
- An agent-foreman task backlog in the project
- Pre-approved tools (allowed-tools): Bash, Read, Glob, Grep, Write, Edit, Task
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- needs_review → may be broken (highest)
- failing → not implemented
- Lower priority number → higher priority (0 is highest)
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:
BashReadGlobGrepWriteEditTask
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 and yaml).
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-Foreman Feature Run loads about 1.6k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 586 words of instructions outside code blocks.
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, Task
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 586 words (~1,649 tokens).
“Mode: Work on all tasks or a specific one”
- name
- feature-run
- allowed-tools
- Bash, Read, Glob, Grep, Write, Edit, Task
- user-invocable
- true
Files
Just SKILL.md in plugins/agent-foreman/skills/feature-run of mylukin/agent-foreman.
Open the folder on GitHubat commit 2763f83
Compare with similar skills
Agent-Foreman Feature Run 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent-Foreman Feature Run this skillmylukin/agent-foreman | 250 | — | ~1.6k | Automated safety check: Notes | None | |
| Spec-Driven Development v2LichAmnesia/lich-skills | 234 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Migrating Claude Agent SDK To Pydantic AIpydantic/pydantic-ai | 21k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Cursor Orchestratecursor/plugins | 11k | — | ~1.1k | Automated safety check: Pass | None | |
| Run Wavejpicklyk/task-orchestrator | 207 | — | ~5k | Automated safety check: Pass | MIT | |
| Optimizeevo-hq/evo | 1.5k | — | ~13k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Migrating Claude Agent SDK To Pydantic AI
pydantic/pydantic-ai
Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.
- Official
Cursor Orchestrate
cursor/plugins
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.
Run Wave
jpicklyk/task-orchestrator
Resolves ready MCP work items into a run plan, shows it to you, then executes it through the Workflow tool or direct subagent dispatch, with post-run verification.
Optimize
evo-hq/evo
Drive structured autoresearch iteration after evo:discover and the baseline commit.
Babysitter Process Runner
a5c-ai/babysitter
Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called…
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.
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.
Agent Task Backlog Initializer
mylukin/agent-foreman
Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.
Project Analyze
mylukin/agent-foreman
Scans codebases to generate architecture documentation (ARCHITECTURE.md). Use when joining an existing project, understanding codebase structure, exploring…
Related
Categories
Questions about Agent-Foreman Feature Run
What does Agent-Foreman Feature Run do?
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. Every task must follow the same sequence: `agent-foreman next` to pick it, implementation, `agent-foreman check`, then `done`. Skipping or reordering steps is forbidden.
When should I use Agent-Foreman Feature Run?
Agent-Foreman Feature Run fits situations like: working through an entire backlog of pending agent-foreman tasks without supervision; completing one named task through the next, implement, check and done cycle; keeping an agent from stopping with half-built features.
How do I install Agent-Foreman Feature Run in Claude Code?
Run `npx skills add mylukin/agent-foreman --skill feature-run -a claude-code`. Or copy the skill folder (plugins/agent-foreman/skills/feature-run in mylukin/agent-foreman) into .claude/skills/feature-run in your project. Claude Code loads it when a task matches its description.
How do I install Agent-Foreman Feature Run in Codex?
Run `npx skills add mylukin/agent-foreman --skill feature-run -a codex`. Or copy the skill folder (plugins/agent-foreman/skills/feature-run in mylukin/agent-foreman) into .agents/skills/feature-run in your project. Codex loads it when a task matches its description.
Can I use Agent-Foreman Feature Run 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 feature-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-run, .gemini/skills/feature-run, .github/skills/feature-run and .opencode/skills/feature-run in your project.
What does Agent-Foreman Feature Run need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent-Foreman Feature Run is instructions for the agent only. Our summary lists: The `agent-foreman` CLI and plugin agents; An agent-foreman task backlog in the project. Its frontmatter pre-approves these tools: Bash, Read, Glob, Grep, Write, Edit, Task.
Does Agent-Foreman Feature Run 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-Foreman Feature Run 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-Foreman Feature Run use?
No licence was found for Agent-Foreman Feature Run or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Agent-Foreman Feature Run use?
About 1.6k tokens (SKILL.md is roughly 6.6k 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-Foreman Feature Run?
Skills that share tags, products or a category with Agent-Foreman Feature Run: Spec-Driven Development v2 (LichAmnesia/lich-skills, 234 stars), Migrating Claude Agent SDK To Pydantic AI (pydantic/pydantic-ai, 21k stars), Cursor Orchestrate (cursor/plugins, 11k stars) and Run Wave (jpicklyk/task-orchestrator, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent-Foreman Feature Run?
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.