القائمة
Agile sprint planning, velocity tracking, and burndown metrics for agent-managed projects
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Onboard a new client/company onto this platform's real Agentic OS: create the company record, scan its websites/repos, auto-provision specialist agents, activate its 24x7 agency runtime, and know exactly which "OS" building blocks (memory, integrations, dashboard) already exist versus which are roadmap gaps. ADAPTED FROM: a third-party giveaway skill ("agentic-os-installer" by Gennaro Santoro / Operations Heroes) that described a generic vault + Google-suite + skill-pack installer. That skill's product (Obsidian vault, Gmail/Calendar/ Drive wiring, "skill packs") does not exist in this repo and its promotional content (Skool community link) does not belong here. This is a clean-room rewrite that keeps the useful idea — "stand up a working agency OS for a client from a short checklist" — and maps every step to the real module that already implements it in this codebase, per CLAUDE.md architecture rules.
Initiative-level portfolio management with dependency tracking and milestone coordination
AI-assisted engineering impact analysis — productivity metrics and code quality insights
Cross-harness agent patterns — standardize agent execution across different coding assistants
Temporal context graph for agent memory — track entity relationships and state changes over time
Andrej Karpathy's coding guidelines for AI agents — concise, correct, and well-tested code
| name | agentic-agile |
| description | Agile sprint planning, velocity tracking, and burndown metrics for agent-managed projects |
Agile sprint management (agents/agile_sprints.py) with velocity tracking,
burndown metrics, and multi-sprint orchestration.
from agents.agile_sprints import AgileManager, AgileSprint, UserStory
mgr = AgileManager()
sprint = mgr.create_sprint("Sprint 5", goal="Ship MVP")
sprint.add_story(UserStory(story_id="s1", title="Login", story_points=5))
sprint.add_story(UserStory(story_id="s2", title="Dashboard", story_points=8))
sprint.start(duration_days=14)
metrics = sprint.get_metrics()
print(f"On track: {metrics.is_on_track}")
m = sprint.get_metrics()
print(m.health) # SprintHealth.AT_RISK
print(sprint.scope_added) # points added since start()
sprint.add_retro_note(went_well="Good pairing", went_poorly="Flaky CI")
sprint.add_action_item("Stabilise CI")
agents/agile_ceremonies.py)Builds standups, retros, and sprint plans straight from
.claude/state/active-tasks.md and the WSJF portfolio — no human input needed.
from agents.agile_ceremonies import (
generate_standup, generate_sprint_retro, generate_backlog_retro,
plan_next_sprint, retrospective_to_markdown,
)
tasks_md = open(".claude/state/active-tasks.md").read()
# Daily standup: Completed / In progress / Planned / Blockers + active sprint health
report = generate_standup(tasks_md, agile_mgr=mgr)
print(report.to_markdown())
# Sprint retro: derived from SprintMetrics.health (complete/on-track/at-risk/
# off-track) plus scope-creep detection; mutates sprint.retrospective in place
retro = generate_sprint_retro(sprint)
# Backlog retro: mines DONE/BLOCKED/DEFERRED rows + the bug log for retro material
retro = generate_backlog_retro(tasks_md)
print(retrospective_to_markdown(retro, "Weekly Backlog Retro"))
# Next-sprint plan: WSJF-allocate portfolio capacity, create the sprint
# (left in PLANNING for a human to start) and add one UserStory per commit
plan = plan_next_sprint(portfolio_mgr, agile_mgr, name="Sprint 9", goal="Ship MVP", capacity=20)
print(plan.to_markdown())
.github/workflows/agile-ceremonies.yml runs .github/scripts/agile_ceremonies.py
on a cron (weekday standup 08:00 UTC, Friday backlog retro 17:00 UTC, Monday
sprint plan 07:00 UTC) and writes the markdown digest to the job summary.
Trigger manually with workflow_dispatch and the ceremony input
(standup / retro / plan).
python -m pytest tests/test_agile_sprints.py tests/test_agile_ceremonies.py -v
agentic-portfolio (initiative/epic level — the layer above)