cli-five 0.1.0

package/templates/.github/agents/reviewer.agent.md

@@ -0,0 +1,88 @@
+---
+name: Reviewer
+description: "Reviews code and agent output for correctness, convention compliance, and architectural alignment. Use when: code review, auditing agent work, validating against specs."
+model: Claude Opus 4.6 (copilot)
+tools: ['read', 'search', 'web', 'vscode/memory']
+agents: []
+user-invocable: true
+---
+
+## Model Selection
+
+| Mode | Model | Premium Cost |
+|---|---|---|
+| **Default** | Claude Opus 4.6 | 3x |
+| **Cheap** | GPT-5 mini | 0x (free) |
+
+To switch: change the `model` key in frontmatter above.
+
+## Subagent Output Contract
+
+When invoked by the Orchestrator, only your **final message** is returned. Internal tool results and earlier turns are invisible.
+
+**Your response MUST use the Review Output Format below.** Always include the explicit `Verdict:` line so the Orchestrator can branch on it.
+
+## Identity
+
+You are a code reviewer. You do NOT write code, fix things, or make changes. You READ, SEARCH, JUDGE, and REPORT.
+
+You are a different agent from the one that wrote the code. The author cannot review their own work.
+
+## Required Reading
+
+Before reviewing, read (if they exist):
+- `decisions.md` — prior team decisions
+- `histories/reviewer.md` — your accumulated learnings
+- `.github/copilot-instructions.md` or `AGENTS.md` — project mandates
+
+## Review Checklist
+
+Every review MUST check against:
+
+1. **Workspace instructions** — Read all `.github/instructions/*.instructions.md` whose `applyTo` glob matches the changed files. Verify compliance.
+2. **Workspace skills** — Read any `.github/skills/*/SKILL.md` or `skills/*/SKILL.md` referenced by the task or matching the changed files. Verify pattern adherence.
+3. **Architecture docs** — If architecture documentation exists (`docs/architecture.md`, `docs/basic-architecture.md`, or equivalent), verify component placement and boundaries.
+4. **Spec/phase docs** — If a spec or phase doc was named in the task, verify the implementation matches.
+5. **General quality** — OWASP Top 10, no leaked secrets, error handling at boundaries, structured logging, testability. Flag tech debt fixable in < 5 minutes.
+
+## Review Output Format
+
+```
+## Review Summary
+**Verdict:** PASS | PASS WITH NOTES | NEEDS CHANGES | REJECT
+
+## Findings
+
+### Critical (must fix before merge)
+- [ ] Finding with file reference and line number
+
+### Warnings (should fix, not blocking)
+- [ ] Finding with file reference and line number
+
+### Notes (observations, suggestions)
+- Finding
+
+### Convention Compliance
+- Workspace instructions: PASS/FAIL (details)
+- Architecture alignment: PASS/FAIL (details)
+- Spec requirements: PASS/FAIL (details)
+
+### What was done well
+- Positive observations
+```
+
+## Decisions
+
+After identifying a convention gap or pattern inconsistency worth documenting, append it to `decisions.md`.
+
+## History
+
+After completing a review, if you learned something non-obvious about this project's quality patterns, append it to `histories/reviewer.md`.
+
+## Rules
+
+- NEVER approve code you haven't read. Read every changed file.
+- NEVER skip the checklist.
+- NEVER suggest improvements that contradict project docs or architecture.
+- Be specific: file path, line number, what's wrong, what should change.
+- If the code is good, say so. Don't invent problems.

package/templates/.github/copilot-instructions.md.tmpl

@@ -0,0 +1,28 @@
+{{PERSONA_BLOCK}}# Project: {{PROJECT_NAME}}
+
+> {{ONE_LINER}}
+
+## Stack
+- {{STACK}}
+
+## Frameworks / Key Libraries
+- {{FRAMEWORKS}}
+
+## Primary Goal
+{{GOALS}}
+
+## Hard Constraints
+{{CONSTRAINTS}}
+
+## Agent Cost Mode
+`{{COST_MODE}}` — change anytime by editing the `model:` line in `.github/agents/*.agent.md`.
+
+# Project Mandates
+- Fix simple tech debt immediately (< 5 min, no downstream breakage).
+- Document short-sighted choices with warning markers.
+- Read `PROJECT.md`, `STATE.md`, and `decisions.md` on entry. Update on exit when relevant.
+
+At the end of every agent session, before stopping, append a terse session summary to `agent-diary.md`
+at the workspace root as a markdown section with format `## YYYY-MM-DD HH:MM` (24-hour time).
+Include: 2-5 sentence summary of what was accomplished, include model used.
+Skip if last entry < 4 minutes ago.

package/templates/.github/instructions/README.md

@@ -0,0 +1,14 @@
+# .github/instructions/
+
+Drop `*.instructions.md` files here for language- or path-specific guidance.
+
+Each file should:
+
+- start with YAML frontmatter
+- include an `applyTo` glob (e.g. `**/*.ts`) OR a `description` for on-demand loading
+- be terse — instructions burn context every time they load
+
+Generate stack-appropriate instructions by running `/agent-customization` in Copilot Chat
+after `npx cli-five init`. It will read `PROJECT.md` and propose files based on your stack.
+
+Reference: https://code.visualstudio.com/docs/copilot/copilot-customization

package/templates/.github/skills/README.md

@@ -0,0 +1,14 @@
+# .github/skills/
+
+Drop project-local skills here as `<skill-name>/SKILL.md` directories.
+
+Skills are on-demand workflows with bundled assets (scripts, templates, references).
+The `description` field IS the discovery surface — without trigger phrases in it, no agent
+will ever load the skill.
+
+Discover community skills:
+
+    npx skills search <term>
+    npx skills add <skill-id>
+
+Sources: https://skills.sh, https://github.com/anthropics/skills, https://github.com/github/awesome-copilot

package/templates/AGENTS.md.tmpl

@@ -0,0 +1,25 @@
+# {{PROJECT_NAME}}
+
+> {{ONE_LINER}}
+
+This file is the tool-agnostic project context. Codex, Cursor, Aider, Gemini CLI, Zed,
+and Copilot all read `AGENTS.md` per the [agents.md](https://agents.md) convention.
+
+## Goal
+{{GOALS}}
+
+## Stack
+{{STACK}}
+
+## Frameworks / Key Libraries
+{{FRAMEWORKS}}
+
+## Constraints
+{{CONSTRAINTS}}
+
+## Workflow
+1. Read `PROJECT.md` for the long-form vision.
+2. Check `STATE.md` for current status, blockers, in-flight decisions.
+3. Check `decisions.md` for architectural decisions already locked in.
+4. Per-agent memory lives in `histories/<agent>.md`.
+5. Append a session summary to `agent-diary.md` when work completes.

package/templates/PROJECT.md.tmpl

@@ -0,0 +1,27 @@
+# {{PROJECT_NAME}} — Project Vision
+
+## One-line
+{{ONE_LINER}}
+
+## Goal
+{{GOALS}}
+
+## Stack
+- {{STACK}}
+
+## Frameworks / Key Libraries
+- {{FRAMEWORKS}}
+
+## Hard Constraints
+{{CONSTRAINTS}}
+
+## Out of Scope
+_(populate as you discover things this project will NOT do)_
+
+## Success Criteria
+_(populate with measurable outcomes — what does "done" look like?)_
+
+---
+
+_This file is the durable vision. It changes rarely. Day-to-day status lives in `STATE.md`._
+_Generated by `npx cli-five` on {{DATE}}._

package/templates/STATE.md.tmpl

@@ -0,0 +1,22 @@
+# {{PROJECT_NAME}} — Current State
+
+> Cross-session memory for all agents. Update on exit; read on entry.
+
+## Status
+_Greenfield. No work performed yet._
+
+## In Flight
+_Open phases, partially-completed tasks, branches awaiting review._
+
+## Blockers
+_What is preventing forward progress?_
+
+## Recent Decisions
+_Last 3-5 entries from `decisions.md`. Or just point to it._
+
+## Next
+_What the next agent invocation should pick up._
+
+---
+
+_Generated by `npx cli-five` on {{DATE}}._

package/templates/agent-diary.md.tmpl

@@ -0,0 +1,5 @@
+# Agent Diary
+
+_Chronological session log. Append-only. Newest at the bottom._
+_Format: `## YYYY-MM-DD HH:MM` (24-hour). 2-5 sentence summary. Always include model used._
+

package/templates/decisions.md.tmpl

@@ -0,0 +1,15 @@
+# Architectural Decisions
+
+> One entry per locked-in choice. Reverse chronological. Concise — not an ADR template.
+
+## Format
+
+    ## YYYY-MM-DD — <decision title>
+    **Context:** Why we needed to decide.
+    **Choice:** What we chose.
+    **Trade-offs:** What we gave up.
+    **Revisit:** Trigger that would re-open this decision (or "never").
+
+---
+
+_No decisions logged yet._

package/templates/histories/coder.md

@@ -0,0 +1,5 @@
+# Coder History
+
+> Accumulated learnings about this project. Read at session start, append non-obvious discoveries.
+
+<!-- Append entries below this line -->

package/templates/histories/designer.md

@@ -0,0 +1,5 @@
+# Designer History
+
+> Accumulated learnings about this project. Read at session start, append non-obvious discoveries.
+
+<!-- Append entries below this line -->

package/templates/histories/orchestrator.md

@@ -0,0 +1,5 @@
+# Orchestrator History
+
+> Accumulated learnings about this project. Read at session start, append non-obvious discoveries.
+
+<!-- Append entries below this line -->

package/templates/histories/planner.md

@@ -0,0 +1,5 @@
+# Planner History
+
+> Accumulated learnings about this project. Read at session start, append non-obvious discoveries.
+
+<!-- Append entries below this line -->

package/templates/histories/reviewer.md

@@ -0,0 +1,5 @@
+# Reviewer History
+
+> Accumulated learnings about this project. Read at session start, append non-obvious discoveries.
+
+<!-- Append entries below this line -->