bryan/agent-team
1
0
Fork 0
mirror of https://github.com/itme-brain/agent-team.git synced 2026-05-08 13:50:12 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: rename plan agent to architect

Browse source
This commit is contained in:
Bryan Ramos 2026-04-01 17:01:44 -04:00
parent e919c91258
commit 8366c09a27
3 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -25,7 +25,7 @@ The script symlinks `agents/`, `skills/`, `CLAUDE.md`, and `settings.json` into
| `senior-worker` | opus | Escalation for architectural complexity or worker failures. | | `senior-worker` | opus | Escalation for architectural complexity or worker failures. |
| `debugger` | sonnet | Diagnoses and fixes bugs with minimal targeted changes. | | `debugger` | sonnet | Diagnoses and fixes bugs with minimal targeted changes. |
| `docs-writer` | sonnet | Writes and updates docs. Never modifies source code. | | `docs-writer` | sonnet | Writes and updates docs. Never modifies source code. |
| `plan` | opus | Research-first planning. Produces implementation plans for workers. Read-only. | | `architect` | opus | Research-first planning. Produces implementation plans for workers. Read-only. |
| `code-reviewer` | sonnet | Reviews diffs for quality, correctness, and coverage. Read-only. | | `code-reviewer` | sonnet | Reviews diffs for quality, correctness, and coverage. Read-only. |
| `security-auditor` | opus | Audits security-sensitive changes for vulnerabilities. Read-only. | | `security-auditor` | opus | Audits security-sensitive changes for vulnerabilities. Read-only. |
| `karen` | opus | Independent fact-checker. Verifies worker output against source and web. Read-only, runs in background. | | `karen` | opus | Independent fact-checker. Verifies worker output against source and web. Read-only, runs in background. |

2
agents/plan.md → agents/architect.md
View file

@ -1,5 +1,5 @@
--- ---
name: Plan name: architect
description: Research-first planning agent. Use before any non-trivial implementation task. Verifies approaches against official documentation and community examples, analyzes the codebase, and produces a concrete implementation plan for workers to follow. description: Research-first planning agent. Use before any non-trivial implementation task. Verifies approaches against official documentation and community examples, analyzes the codebase, and produces a concrete implementation plan for workers to follow.
model: opus model: opus
effort: max effort: max

10
skills/orchestrate/SKILL.md
View file

@ -16,7 +16,7 @@ You (orchestrator)
├── docs-writer (sonnet, effort: high) — READMEs, API refs, architecture docs, changelogs; never touches source ├── docs-writer (sonnet, effort: high) — READMEs, API refs, architecture docs, changelogs; never touches source
├── requirements-analyst (sonnet, read-only) — first planning stage: tier classification, constraints, research questions ├── requirements-analyst (sonnet, read-only) — first planning stage: tier classification, constraints, research questions
├── researcher (sonnet, read-only) — one per topic, parallel; verified facts from docs and community ├── researcher (sonnet, read-only) — one per topic, parallel; verified facts from docs and community
├── plan (opus, effort: max) — architect: receives requirements + research, produces implementation blueprint ├── architect (opus, effort: max) — architect: receives requirements + research, produces implementation blueprint
├── decomposer (sonnet, read-only) — translates plan into parallelizable worker task specs ├── decomposer (sonnet, read-only) — translates plan into parallelizable worker task specs
├── code-reviewer (sonnet, read-only) — quality gate: logic, naming, error handling, test coverage ├── code-reviewer (sonnet, read-only) — quality gate: logic, naming, error handling, test coverage
├── security-auditor (opus, read-only) — vulnerability audit: injection, auth, secrets, crypto, OWASP ├── security-auditor (opus, read-only) — vulnerability audit: injection, auth, secrets, crypto, OWASP
@ -46,7 +46,7 @@ Determine before starting. Default to the lowest applicable tier.
**Cost-aware shortcuts:** **Cost-aware shortcuts:**
- Tier 1 with obvious approach: skip the planning pipeline entirely — spawn worker directly - Tier 1 with obvious approach: skip the planning pipeline entirely — spawn worker directly
- Tier 1 with uncertain approach: spawn `plan` directly (skip requirements-analyst and researcher) - Tier 1 with uncertain approach: spawn `architect` directly (skip requirements-analyst and researcher)
- Tier 2+: run the full pipeline - Tier 2+: run the full pipeline
- When in doubt, err toward shipping — the review chain catches mistakes cheaper than the planning pipeline prevents them - When in doubt, err toward shipping — the review chain catches mistakes cheaper than the planning pipeline prevents them
@ -80,12 +80,12 @@ Each researcher receives:
Collect all researcher outputs. Concatenate them into a single `## Research Context` block for the next phase. Collect all researcher outputs. Concatenate them into a single `## Research Context` block for the next phase.
**Phase 3 — Architecture and planning** **Phase 3 — Architecture and planning**
Spawn `plan` with three inputs assembled as a single prompt: Spawn `architect` with three inputs assembled as a single prompt:
- Requirements analysis output (from Phase 1) - Requirements analysis output (from Phase 1)
- Research context block (from Phase 2, or "No research context — approach uses established codebase patterns." if Phase 2 was skipped) - Research context block (from Phase 2, or "No research context — approach uses established codebase patterns." if Phase 2 was skipped)
- The original raw user request - The original raw user request
Pass the tier so the plan agent selects the appropriate output format (Brief or Full). Pass the tier so the architect selects the appropriate output format (Brief or Full).
### Step 4 — Consume the plan ### Step 4 — Consume the plan
@ -193,7 +193,7 @@ When the plan includes risk tags, use this table to determine mandatory reviewer
| `external-api` | `karen` | Verify API usage against documentation | | `external-api` | `karen` | Verify API usage against documentation |
| `data-mutation` | `verification` | Must validate writes to persistent storage at runtime | | `data-mutation` | `verification` | Must validate writes to persistent storage at runtime |
| `breaking-change` | `karen` | Verify downstream impact, check AC coverage | | `breaking-change` | `karen` | Verify downstream impact, check AC coverage |
| `new-library` | `karen` | Verify usage against docs; planner must do full research first | | `new-library` | `karen` | Verify usage against docs; architect must do full research first |
| `concurrent` | `verification` | Concurrency bugs are hard to catch in static review | | `concurrent` | `verification` | Concurrency bugs are hard to catch in static review |
When multiple risk tags are present, take the union of all mandatory reviewers. When multiple risk tags are present, take the union of all mandatory reviewers.