agentic-engineering
v0.5.3by calorie · author: Agentic Engineering Maintainers
Minimal runtime-neutral engineering policy with proactive execution optimization and objective-level review DAG planning for one, independent, or Stacked PR topology.
Package we checked
The manifest we fetched is plugins/agentic-engineering/plugin.json in calorie/agentic-engineering. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 2 skills (orchestrate, stacked-pr) and no MCP servers. Extension keys: com.openai.
What agentic-engineering does, in the publisher's words
Agentic Engineering is a deliberately small policy plugin for Claude Code and Codex.
It does not implement its own scheduler, context engine, worker pool, or hook runtime. Instead, it tells native runtimes to automatically optimize execution around a user-provided engineering objective.
Current version: 0.5.3
- Superpowers provides methodology such as TDD, systematic debugging, and verification. Do not nest another scheduler under an active native scheduler.
- Ponytail biases implementation toward the simplest correct solution. Explicit requirements, safety, and project invariants take precedence.
- important long-lived design decisions that cannot be inferred safely;
- the final action that integrates changes into the default branch, such as merging a PR or directly merging/pushing to the default branch.
- one focused reviewable unit -> one PR;
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 2
- MCP servers
- 0
- Stars
- 0
- License
- n/a
- Repo created
- 2026-09-20
- Last pushed
- 2026-10-26
- Publisher type
- User
- Version
- 0.5.3
Links
Skills · 2
- orchestrate
- Automatically optimize substantive software work using runtime-native capabilities. Proactively protect context, delegate and parallelize beneficial work, persist durable state for long-running tasks, deduplicate verification, and choose review topology without making the user manage orchestration.
- stacked-pr
- Use GitHub native stacked pull requests when changes are dependent but independently reviewable. Do not stack independent work or a single focused change.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
software-engineering · orchestration · dynamic-workflows · codex · worktree · stacked-pr · superpowers · ponytail
Related by publisher and keywords
Open-source engineering skills for repository work, Python, host-native MARGOS orchestration, ReThinking audits, and Agent Plugins authoring.
The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.
Agent skills for research, App Store readiness, Codex model routing, repository and Swift review, PR feedback triage, and safe branch cleanup.
사용자 의도를 먼저 판별하고, 제품·기능·연구 실험·버그에 맞는 서로 다른 승인 흐름을 적용하는 한국어 워크플로우입니다.
Orchestrate complex multi-task work by separating advisor reasoning, delegated execution, and independent verification until tasks converge.
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
[](https://agentpluginsdirectory.com/plugins/agentic-engineering)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.