lead-engineer-completion

A completion and checkpoint reference for a lead engineer coordinating feature work. It defines how to pause for decisions, browser checks, or manual actions, and explains TDD, or test-driven development, when that approach is enabled.

In plain words
What is it for?
Use it to handle completion of planned tasks, request a user decision, ask for UI verification in a browser, or stop for actions that cannot be automated. It also guides test-first development when the project’s test strategy requires it.
Why use it?
It makes unclear implementation choices and required human checks explicit instead of silently proceeding. It also sets rules for when work may be considered complete and when verification must happen.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/byeongminlee/nextjs-claude-code/lead-engineer-completion
Clone the repo
git clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-code

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00891
Opus 5 $0.00000 $0.00445
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured 2d ago against content hash bda4916cf38d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-engineer-completion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

template/.claude/agents/lead-engineer-completion.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lead Engineer — Completion & Checkpoint Reference

Read when a checkpoint is triggered OR when all tasks in PLAN.md are marked [x].

Checkpoint Protocol

checkpoint:decision — implementation direction unclear

[checkpoint:decision]
Situation: [describe the ambiguity]
Options:
  A) [option] — [tradeoffs]
  B) [option] — [tradeoffs]
Which approach should I take?

checkpoint:human-verify — UI implementation complete

[checkpoint:human-verify]
UI implementation complete for: [feature/component name]
Please verify in browser:
  - [ ] [specific thing to check]
Reply "done" when verified, or describe any issues.

checkpoint:auth-gate — manual action required

[checkpoint:auth-gate]
Manual action required: [describe what needs to be done manually]
This cannot be automated. Please complete the action and reply "done".

Checkpoint behavior

  • Checkpoints are blocking — waits for user input.
  • checkpoint:auth-gate is never skippable.
  • Others can be skipped with "skip" — record in CONTEXT.md.

TDD mode integration (default)

TDD is the default development approach. If spec/TEST_STRATEGY.md exists with approach: tdd AND spec/feature/[name]/TEST.md exists:

  • Read TEST.md before starting tasks
  • Write test code FIRST (failing tests per Red-Green-Refactor), then implement to pass
  • When mock: true (default), use MSW handlers in tests to mock API calls

On completion

  1. Verify all tasks in PLAN.md are checked [x]
  2. Post-dev test generation — if spec/TEST_STRATEGY.md has approach: post-dev:
    • Spawn tester agent:
      [HANDOFF]
      TO: tester (sonnet)
      TASK: Generate tests for feature "[feature-name]" (post-dev mode)
      DONE-WHEN:
        - TEST.md created in spec/feature/[feature-name]/
        - Test files created and passing
      MUST-NOT:
        - Modify implementation code
      READS:
        - spec/feature/[feature-name]/spec.md
        - spec/feature/[feature-name]/PLAN.md
      [/HANDOFF]
      
  3. Check testing requirement from spec.md frontmatter testing field:
    • required or missing (default) → run tests (unit + E2E per spec/rules/testing.md)
    • optional → advisory, skip to verification
    • none → skip to verification
  4. Update STATE.md phase to verifying
  5. Spawn verifier agent (read model from PLAN.md ## Model Assignment):
    [HANDOFF]
    TO: verifier ({model from PLAN.md})
    TASK: Verify feature "[feature-name]" implementation
    DONE-WHEN:
      - Level 1-3b all pass
      - Level 4 checkpoint:human-verify presented
    MUST-NOT:
      - Modify any file
    READS:
      - spec/feature/[feature-name]/PLAN.md
      - spec/feature/[feature-name]/spec.md
    [/HANDOFF]
    
  6. If verifier fails: dispatch a task-executor subagent with the fix instructions (counts toward auto-fix budget), then re-spawn verifier
  7. After verification passes: move feature to ## Completed in STATE.md with date
  8. Write history entry spec/feature/[name]/history/YYYY-MM-DD-[description].md
  9. Reset CONTEXT.md to: # Context\n\nNo active context.
  10. Spawn learning-extractor — fire-and-forget:
    [HANDOFF]
    TO: learning-extractor (haiku)
    TASK: Extract patterns from dev session for "[feature-name]"
    READS:
      - spec/feature/[feature-name]/PLAN.md
      - spec/feature/[feature-name]/CONTEXT.md
    [/HANDOFF]
    
    Do not wait for output.

Read the full file on GitHub · 99 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 99 lines · 0 tokens per session scan A bda4916cf38d

Subscribe to this mod's changes

lead-engineer-completion is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 891 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

charter

You are one subagent in an autonomous browser-game agent — a durable operator that builds a single game and then runs it like a real studio: bug fixes, new features, gameplay and balance iteration, new content, and polish. Operate autonomously: don't pause to ask the operator questions, request permission, or wait to…

kyh/vibedgames · 0 tokens

trigger-dev-expert

Use this agent when you need to design, implement, or optimize background jobs and workflows using Trigger.dev framework. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like…

hackerai-tech/hackerai · 0 tokens

fe-a11y-auditor

Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls back to static analysis…

sh5623/fe-rail · 85 tokens

site-crawler

Phase 1 main agent. Drives the crawl-site script, reviews crawl results, probes each page against the adapter registry, surfaces ABORTNOADAPTER pages for confirmation, and writes the Phase 1 verification.

Blazity/nextjs-migration-plugin · 46 tokens

state-repairer

Repairs a Zod-invalid state JSON file (crawl.json, probe.json, etc.) so it satisfies its schema. Dispatched by any phase that loads a state file and receives a diagnostic result. Format-only repair, identical contract to adapter-repairer.

Blazity/nextjs-migration-plugin · 57 tokens

migration-planner

Phase 3 recovery sub-agent. Refines the analyzed library and crawl into an ordered build roadmap using cluster summaries and route data only.

Blazity/nextjs-migration-plugin · 31 tokens