feat(agentic-engineering)!: rename entrypoint to agentic-engineer - #89
Conversation
The plugin consolidated on the `agentic-engineering` identity in ADR 0004 but kept the primary engineer's entrypoint named `automated-ai-engineer`, so the role carried two names: consumers installed `agentic-engineering`, read about the Agentic Engineer in prose, then wired a schedule to `automated-ai-engineer`. Rename the entrypoint, the agent file, and every prose reference to `agentic-engineer` / "Agentic Engineer". Historical records keep their original wording: ADRs 0002-0004, the append-only marketplace `renames` map, and `marketplace-rename-history.json` are untouched — the rename map is a persisted consumer contract that must never lose an entry. Major bump to 3.0.0: a persisted `plugin:agentic-engineering/automated-ai-engineer` pointer or a qualified `agentic-engineering:automated-ai-engineer` reference stops resolving, and there is no marketplace-level rename migration for agent names. ADR 0005 records the decision; the plugin README carries the migration checklist. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
…er-rename-schedules # Conflicts: # .claude-plugin/marketplace.json # .github/plugin/marketplace.json # README.md # plugins/agentic-engineering/.claude-plugin/plugin.json # plugins/agentic-engineering/README.md # plugins/agentic-engineering/plugin.json # plugins/agentic-engineering/resources/provider-neutral.desired-state.json # scripts/validate-manifests.sh
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
@coderabbitai review |
|
✅ Action performedReview finished.
|
📝 WalkthroughWalkthroughThe Possibly related issues
Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
@coderabbitai review |
|
✅ Action performedReview finished.
|
![coderabbitai[bot]](https://cdn.github.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@plugins/agentic-engineering/skills/portfolio-maintenance/SKILL.md`:
- Line 30: Update the canonical upstream definitions with the contract-reference
rename, then regenerate all bundled copies through update-agent-skills:
plugins/agentic-engineering/skills/portfolio-maintenance/SKILL.md lines 30-30,
plugins/agentic-engineering/skills/product-engineering/SKILL.md lines 22-22, and
plugins/agentic-engineering/skills/self-improvement/SKILL.md lines 21-21. Do not
edit these synchronized SKILL.md files directly.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: d8aa9131-3161-438c-b4e8-82a88ad075fc
📒 Files selected for processing (16)
.claude-plugin/marketplace.json.github/plugin/marketplace.jsonAGENTS.mdREADME.mddocs/adr/0006-rename-agentic-engineer-entrypoint.mdplugins/agentic-engineering/.claude-plugin/plugin.jsonplugins/agentic-engineering/README.mdplugins/agentic-engineering/agents/agentic-engineer.agent.mdplugins/agentic-engineering/agents/portfolio-surveyor.agent.mdplugins/agentic-engineering/plugin.jsonplugins/agentic-engineering/resources/provider-neutral.desired-state.jsonplugins/agentic-engineering/skills/portfolio-maintenance/SKILL.mdplugins/agentic-engineering/skills/product-engineering/SKILL.mdplugins/agentic-engineering/skills/self-improvement/SKILL.mdscripts/validate-manifests.shscripts/validate-manifests.test.sh
📜 Review details
🧰 Additional context used
📓 Path-based instructions (9)
plugins/*/plugin.json
📄 CodeRabbit inference engine (AGENTS.md)
Each plugin must have a portable
plugins/<name>/plugin.jsonwith kebab-case name, description, version, and no component-path fields; resources are auto-discovered from directories.
Files:
plugins/agentic-engineering/plugin.json
plugins/*/.claude-plugin/plugin.json
📄 CodeRabbit inference engine (AGENTS.md)
Each plugin must have an equivalent strict Claude manifest at
plugins/<name>/.claude-plugin/plugin.json, semantically identical to its portable manifest.
Files:
plugins/agentic-engineering/.claude-plugin/plugin.json
plugins/*/skills/*/SKILL.md
📄 CodeRabbit inference engine (AGENTS.md)
Every bundled
SKILL.mdmust conform to the agentskills.io specification and retain non-emptymetadata.github-repoprovenance.
Files:
plugins/agentic-engineering/skills/portfolio-maintenance/SKILL.mdplugins/agentic-engineering/skills/self-improvement/SKILL.mdplugins/agentic-engineering/skills/product-engineering/SKILL.md
{.claude-plugin,.github/plugin}/marketplace.json
📄 CodeRabbit inference engine (AGENTS.md)
Keep
.claude-plugin/marketplace.jsonand.github/plugin/marketplace.jsonsemantically identical, updating both whenever the plugin set changes.
Files:
.github/plugin/marketplace.json.claude-plugin/marketplace.json
plugins/*/agents/*.agent.md
📄 CodeRabbit inference engine (AGENTS.md)
Custom agents must use the
.agent.mdsuffix and YAML frontmatter containing non-emptynameanddescriptionfields.
Files:
plugins/agentic-engineering/agents/portfolio-surveyor.agent.mdplugins/agentic-engineering/agents/agentic-engineer.agent.md
plugins/*/resources/*.desired-state.json
📄 CodeRabbit inference engine (AGENTS.md)
Desired-state resources must use the provider-neutral schema, include the required consumer contract, contain no placeholders, and be explicitly linked from the owning plugin README.
Files:
plugins/agentic-engineering/resources/provider-neutral.desired-state.json
README.md
📄 CodeRabbit inference engine (AGENTS.md)
Keep the README plugin table in lockstep with the manifests and filesystem: every plugin has one row, every row maps to a plugin, and Resources reflects discovered skills, MCP servers, and agents; ancillary resources are documented in the plugin README instead.
Files:
README.md
scripts/*.sh
📄 CodeRabbit inference engine (AGENTS.md)
Keep
scripts/validate-manifests.shas the single source of truth for manifest, parity, README, desired-state, and provenance validation; do not weaken checks to make CI pass.
Files:
scripts/validate-manifests.shscripts/validate-manifests.test.sh
scripts/validate-manifests.test.sh
📄 CodeRabbit inference engine (AGENTS.md)
The manifest validator self-test must pass both a consistent fixture and each drift scenario the validator is expected to reject.
Files:
scripts/validate-manifests.test.sh
🧠 Learnings (2)
📓 Common learnings
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Use Conventional Commit types such as `feat:`, `fix:`, `chore:`, `ci:`, `docs:`, and `refactor:` for commit messages and PR titles.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Never hand-edit bundled `SKILL.md` files to diverge from upstream; fix the upstream skill and let the update workflow import the change.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Keep marketplace names, descriptions, and README framing tool-neutral across VS Code, Copilot CLI, and Claude Code.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Record every plugin rename or removal in the append-only `renames` map in both marketplace manifests and in `scripts/marketplace-rename-history.json`; preserve valid chains to a current name or `null`.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Validate before every PR, fix root causes, never weaken security controls or checks, and never push directly to `main`.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Begin every PR, issue, or comment with `> 🤖 Generated by the Agentic Engineer`.
Learnt from: CR
Repo: devantler-tech/agent-plugins
Timestamp: 2026-07-25T12:31:44.474Z
Learning: Work in per-run worktrees and never merge external PRs; drive trusted-author PRs toward merge only after required checks are green and review threads are resolved.
📚 Learning: 2026-06-28T12:17:58.373Z
Learnt from: devantler
Repo: devantler-tech/agent-plugins PR: 36
File: plugins/engineering-practices/skills/conventional-release/SKILL.md:57-59
Timestamp: 2026-06-28T12:17:58.373Z
Learning: Bundled skill artifact files at `plugins/*/skills/*/SKILL.md` are synced from upstream and must not be hand-edited locally. If you need to change a skill, update the corresponding upstream skill repository first, then pull the updated artifact into this repo using the `update-agent-skills` workflow (and review the resulting diff for the synced contents).
Applied to files:
plugins/agentic-engineering/skills/portfolio-maintenance/SKILL.mdplugins/agentic-engineering/skills/self-improvement/SKILL.mdplugins/agentic-engineering/skills/product-engineering/SKILL.md
🪛 LanguageTool
plugins/agentic-engineering/README.md
[style] ~26-~26: To elevate your writing, try using more formal phrasing here.
Context: ...oyment that persists the old entrypoint keeps pointing at an agent that no longer resolves. Up...
(CONTINUE_TO_VB)
[style] ~101-~101: Consider using “who” when you are referring to a person instead of an object.
Context: ...: - agentic-engineer — the actor that runs the survey → select → act → report...
(THAT_WHO)
🪛 markdownlint-cli2 (0.23.0)
plugins/agentic-engineering/agents/portfolio-surveyor.agent.md
[warning] 15-15: First line in a file should be a top-level heading
(MD041, first-line-heading, first-line-h1)
plugins/agentic-engineering/agents/agentic-engineer.agent.md
[warning] 25-25: First line in a file should be a top-level heading
(MD041, first-line-heading, first-line-h1)
🪛 SkillSpector (2.3.11)
plugins/agentic-engineering/skills/product-engineering/SKILL.md
[warning] 94: [EA2] Autonomous Decision Making: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Remediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
(Excessive Agency (EA2))
🔇 Additional comments (13)
docs/adr/0006-rename-agentic-engineer-entrypoint.md (1)
1-57: LGTM!.claude-plugin/marketplace.json (1)
30-30: 🗄️ Data Integrity & Integration🤖 Generated by the Agentic Engineer
Verify marketplace semantic parity after this version bump.
Confirm
.claude-plugin/marketplace.jsonstill matches.github/plugin/marketplace.json, including plugin entries, versions, descriptions, sources, and the append-onlyrenamesmap. Otherwise supported tools may consume different catalogs.As per coding guidelines, both marketplace manifests must remain semantically identical.
Based on learnings, this review comment begins with the required generated marker.
Sources: Coding guidelines, Learnings
.github/plugin/marketplace.json (1)
30-30: LGTM!plugins/agentic-engineering/.claude-plugin/plugin.json (1)
4-4: LGTM!plugins/agentic-engineering/plugin.json (1)
4-4: LGTM!AGENTS.md (1)
199-201: LGTM!Also applies to: 212-212
README.md (1)
17-17: LGTM!Also applies to: 89-102, 172-172
scripts/validate-manifests.test.sh (1)
561-563: LGTM!Also applies to: 588-588, 598-604, 630-630, 651-653, 768-768, 799-803, 942-943
plugins/agentic-engineering/README.md (1)
14-42: LGTM!Also applies to: 80-90, 101-101, 134-134
plugins/agentic-engineering/agents/agentic-engineer.agent.md (1)
2-2: LGTM!Also applies to: 25-25
plugins/agentic-engineering/agents/portfolio-surveyor.agent.md (1)
4-4: LGTM!Also applies to: 15-15
plugins/agentic-engineering/resources/provider-neutral.desired-state.json (1)
12-12: LGTM!Also applies to: 38-38, 59-61, 94-94
scripts/validate-manifests.sh (1)
521-523: LGTM!Also applies to: 566-566, 589-589, 663-665, 788-793
These carry `metadata.github-repo: devantler-tech/agent-skills` provenance, so they are synchronized artifacts, not authored here. Editing them downstream is exactly what this repo's conventions forbid, and the daily `update-agent-skills` sync would have silently reverted the rename on its next run. The same change is applied upstream in devantler-tech/agent-skills#80 and will arrive here through the sync workflow. The bundled copies therefore keep saying "Automated AI Engineer plugin" until that lands, which is the correct intermediate state rather than a miss. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
|
@coderabbitai review |
|
✅ Action performedReview finished.
|
Readiness at
|
…neer Rebuild #87 onto the renamed entrypoint after #89. Draft remains the checkpoint; self-promote only on genuine readiness, then merge. Bundled skill bodies stay upstream (agent-skills#76); do not hand-edit. Bump plugin 4.1.0 → 4.1.1 so the content change reaches consumers. Fixes #85 Co-authored-by: ned <ned@devantler.tech>
1 participant
Why
The plugin already installs as
agentic-engineeringand its docs already call the role the Agentic Engineer — but the actual entrypoint you wire a schedule to was still calledautomated-ai-engineer. One role, two names, and every new deployment pays that confusion cost during onboarding.What
Renames the primary engineer entrypoint and every prose reference to
agentic-engineer/ "Agentic Engineer".Breaking — major bump to 4.0.0. A persisted
plugin:agentic-engineering/automated-ai-engineerschedule pointer or a qualifiedagentic-engineering:automated-ai-engineeragent reference stops resolving. Unlike plugin renames, agent renames have no automatic marketplace migration, so consumers update three places by hand; the plugin README carries a Migrating to version 4 checklist, sequenced to run after the v3 spend migration so a failed reconcile stays attributable to one cause.Rebased onto the spend-stewardship merge (#90), which took
3.0.0and ADR 0005 while this was in flight — hence 4.0.0 and ADR 0006.Historical records are deliberately untouched — ADRs 0002–0005, the append-only marketplace
renamesmap, andmarketplace-rename-history.json. The rename map is a persisted consumer contract that must never lose an entry.