engineering-foundation-core
v0.3.0-beta.2Task contracts, bounded planning and orchestration, surgical implementation, debugging, research, review, verification, and handoff.
What engineering-foundation-core does, in the publisher's words
Provider-neutral engineering contracts and workflows for ordinary coding work.
This package contains nine portable Agent Skills. Install it for general engineering work; Laravel, design, cloud, and authoring concerns remain separate so discovery context stays small.
Provider manifests live under.codex-plugin/ and.claude-plugin/. Repository-level validation and packaging are owned by the project root.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 9
- MCP servers
- 0
- Stars
- 0
- License
- MIT
- Repo created
- 2026-08-14
- Last pushed
- 2026-08-19
- Publisher type
- User
- Version
- 0.3.0-beta.2
Links
Skills · 9
- bounded-orchestration
- Choose between one accountable agent and bounded delegation for independent research, review, verification, or disjoint workstreams. Use when a task has genuinely separable work. Do not use to fan out small tasks, duplicate implementation, overlap writers, or create recursive agent chains.
- handoff
- Produce a compact, durable transfer packet for another session, agent, machine, or provider while preserving decisions, repository state, evidence, risks, and the next atomic action. Use when context is ending, work changes owner, or a handoff is requested. Do not dump the full transcript, raw logs…
- plan-and-milestones
- Create and maintain an executable plan with decisions, risks, milestones, validation, and stop conditions. Use for cross-cutting, uncertain, high-risk, migration, or multi-session work. Do not use for a small localized change that can be implemented and verified directly.
- review-diff
- Review a proposed diff against its task contract for correctness, regressions, security, compatibility, tests, and maintainability. Use after a material implementation reaches a reviewable state or when review is requested. Do not use to rewrite code for taste, manufacture style findings, or create…
- source-grounded-research
- Research current, niche, version-sensitive, or disputed technical facts using primary sources and provenance. Use when a decision depends on information that may have changed or differs by provider/version. Do not use external research when repository evidence is sufficient or paste untrusted web i…
- surgical-implementation
- Implement an accepted change with the smallest coherent diff, repository-local conventions, focused tests, and one bounded cleanup before final verification. Use when modifying code or configuration. Do not use for open-ended redesign, drive-by cleanup, or post-success rewrites.
- systematic-debugging
- Diagnose a reproducible defect through evidence, ranked hypotheses, isolation, a minimal fix, and a regression guard. Use for failures, flaky tests, performance regressions, unexpected behavior, or unclear root causes. Do not use random patches as experiments or for ordinary feature implementation.
- task-contract
- Define a compact task contract with objective, acceptance IDs, non-goals, constraints, evidence, risk, and reopen conditions. Use when starting implementation, debugging, review, or durable work. Do not use to create ceremony for an obvious one-line edit.
- verify-before-completion
- Build an evidence matrix and gate completion on current command output, runtime observations, artifacts, and diff inspection. Use before claiming implementation, debugging, review fixes, milestones, or handoffs are complete. Do not use to infer, invent, recycle stale, or omit required evidence.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
engineering · planning · verification · review · handoff · research · multi-agent
Related by publisher and keywords
Author and maintain compact Agent Skills and plugin packages with precise triggers, progressive disclosure, provenance, validation, and eval coverage.
Codex Cloud and remote-agent environment readiness with idempotent setup, bounded network access, secret safety, caching, and reproducible checks.
Single-direction interface design, design-contract authoring, implementation states, accessibility, and rendered visual verification.
Repository-aware Laravel and PHP engineering using installed versions, local conventions, database evidence, tests, and Laravel Boost when present.
Engineering workflow skills for decision mapping, adversarial design review, dependency maintenance, durable terminology, decision records, prototyping, TDD, diagnosis, architecture, code review, and handoffs.
Codex engineering with Astra XHIGH planning and advice, Luna MAX Fast workers, Sol MAX design, independent Sol review, and context isolation.
[](https://agentpluginsdirectory.com/plugins/engineering-foundation-core)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.