Observed since 21 Oct, 09:07 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
agileforagents
Turn any project idea into a verified, sprint-ready agile task board — inside your AI coding agent
Turn any project idea into a structured, sprint-ready task board — instantly, inside your AI coding agent.
Stop starting with a blank file. Describe what you want to build and AgileForAgents hands your agent a complete, verified plan: epics broken into sprints, user stories, subtasks with clear done-criteria, and every assumption made explicit — so your agent executes with precision instead of guessing.
Works in Claude Code, Cursor, Codex CLI, and any MCP-compatible environment. No account, no API key, no configuration required.
pip install agileforagents
Requires Python 3.11 or later.
Then register it with your MCP host.
Claude Code (~/.claude/mcp.json or your project's .mcp.json):
{
"mcpServers": {
"agileforagents": {
"command": "agileforagents"
}
}
}
Cursor / Codex CLI: point your MCP config at the agileforagents command. No environment variables required.
| Tool | What it does |
|---|---|
generate_agile_tasks | Takes your idea (however vague) and returns a verified, sprint-ready board. Supports format: claude, json, or cursor; and detail_level: standard or detailed. |
get_agent_rules | Returns a ready-to-paste working protocol for your agent — drop it into CLAUDE.md or .cursorrules. |
feedback_stats | Shows how many boards you've generated locally. |
Just describe your project naturally — AgileForAgents handles the planning:
"Build a subscription billing system with Stripe, user portal, and email receipts"
Your agent receives back a complete board with epics, sprints, user stories, and subtasks — each with an observable done-criteria — ready to execute immediately.
Example output (abbreviated):
## Project Goal
Deliver a subscription billing system with Stripe payments, self-service
user portal, and transactional email receipts.
## Sprint 1 — Core Billing
- [ ] Integrate Stripe Checkout for plan selection
Done: Checkout session created, webhook receives payment confirmation
- [ ] Store subscription state in Postgres
Done: subscriptions table seeded, status transitions tested
...
If the backend is temporarily unavailable, AgileForAgents returns a heuristic scaffold automatically — no error, no interruption. The board is marked as offline mode so you know to review it before executing.
Note: The first request after a period of inactivity may take up to 60 seconds while the backend warms up. Subsequent requests are fast.
Board generation hangs for 60+ seconds on first use The backend may be cold-starting. Wait up to 90 seconds; it will complete. Subsequent requests in the same session are fast.
Board returned says "Generated in offline mode" The backend was temporarily unreachable. The heuristic scaffold is a useful starting point — review and refine before handing to your agent.
agileforagents command not found after install
Ensure the Python scripts directory is on your PATH. With a virtual environment: activate it first. With pipx: pipx install agileforagents.
MCP host shows the tool but calls fail
Restart your MCP host after installing or upgrading. Claude Code: /mcp → reconnect. Cursor: reload window.
pip install -e ".[dev]"
make format-check && make lint && make typecheck && make test
See CHANGELOG.md.
MIT
Download counts and popularity will appear here as the collector receives them.
| Package / target | Requirement | Relationship |
|---|---|---|
mcpEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | mcp>=1.9.0 | runtime |
pydanticEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | pydantic>=2.0.0 | runtime |
pytestEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | pytest>=8.0.0; extra == "dev" | runtime |
pytest-covEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | pytest-cov>=5.0.0; extra == "dev" | runtime |
pytest-asyncioEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | pytest-asyncio>=0.23.0; extra == "dev" | runtime |
ruffEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | ruff>=0.4.0; extra == "dev" | runtime |
mypyEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | mypy>=1.10.0; extra == "dev" | runtime |
pip-auditEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.11",
"evaluation": "NOT_EVALUATED"
} | pip-audit>=2.7.0; extra == "dev" | runtime |
bdist_wheel · 19.57 KB · Python py3
sdist · 23.25 KB · Python source
Observed since 21 Oct, 09:07 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package_version:fce3912e9815f3f1584187b8eda3585cc2976a922abc87fa7dabd3982d6b371f