Skip to content
Development
Command

/6-complete

**Navigation**: [<- Step 5: Validate](5-validate.md) | [Main Workflow](../workflow-steps.md)

From plugin
claude-night-market
325163 skills59 agents163 commands1 MCP
Install
$ npx -y skills add athola/claude-night-market --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/6-complete

Context preview

What this command does when you run it.

**Navigation**: [<- Step 5: Validate](5-validate.md) | [Main Workflow](../workflow-steps.md)

Command definition

6-complete.md

Step 6: Complete (Threads, Issues, Summary)

> **Navigation**: [<- Step 5: Validate](5-validate.md) | [Main Workflow](../workflow-steps.md)

**Purpose**: Resolve threads, create issues for deferred items, and post summary.

**Platform Note**: Commands below show GitHub (`gh`) examples. Check session context for `git_platform:` and consult `Skill(leyline:git-platform)` for GitLab (`glab`) / Bitbucket equivalents. GitLab uses "merge request" terminology and `glab api graphql` for thread resolution.

**CRITICAL WORKFLOW GUARDRAIL**

**NEVER skip this step unless you are NOT the PR author. If you are the PR author and received review comments, you MUST complete this step. There are NO exceptions.**

Load: [Pre-Check](6-complete/pre-check.md)

**If you are NOT the PR author**, you may skip to Step 6.4. Otherwise, continue below.

---

Sub-Module Navigation

Step 6 is organized into sub-modules. Execute them in order:

| Sub-Step | Module | Purpose | |----------|--------|---------| | **Pre** | [Pre-Check](6-complete/pre-check.md) | Validate reviews submitted and threads resolved | | **6.0** | [Reconciliation](6-complete/reconciliation.md) | Reconcile ALL unworked items and enforcement | | **6.1-6.2** | [Issue Creation](6-complete/issue-creation.md) | Create issues for suggestions and deferred items | | **6.3** | [Thread Resolution](6-complete/thread-resolution.md) | Reply to and resolve every review thread | | **6.4** | [Issue Linkage](6-complete/issue-linkage.md) | Link/close related issues | | **6.5** | [Summary](6-complete/summary.md) | Post summary comment to PR | | **6.6** | [Verification](6-complete/verification.md) | Final verification and workflow gate | | **6.7** | Tooling Reflection | Post night-market tooling observations to Discussions |

---

Sub-Step 6.7: Tooling Reflection (Night-Market Feedback Loop)

After completing the workflow, reflect on the *tooling itself* (skills, agents, commands, hooks) rather than the repo code.

**Ask yourself:**

  • Did any skill behave unexpectedly or have unclear guidance?
  • Was an agent slow, redundant, or missing context?
  • Did a command skip steps it shouldn't have, or require

unnecessary manual intervention?

  • Did a hook fire incorrectly or miss a case?

**If yes**, post to the **night-market** GitHub Discussions (Learnings category). Always target https://github.com/athola/claude-night-market/discussions, not the current repo:

# Always target the night-market repo for tooling feedback
NM_OWNER="athola"
NM_REPO="claude-night-market"

NM_REPO_ID=$(gh api graphql \
  -f query="query { repository(owner: \"$NM_OWNER\", name: \"$NM_REPO\") { id } }" \
  --jq '.data.repository.id')

NM_CAT_ID=$(gh api graphql \
  -f query="query { repository(owner: \"$NM_OWNER\", name: \"$NM_REPO\") { discussionCategories(first: 20) { nodes { id slug } } } }" \
  --jq '.data.repository.discussionCategories.nodes[] | select(.slug == "learnings") | .id')

gh api graphql -f query='mutation($repoId: ID!, $categoryId: ID!, $title: String!, $body: String!) {
  createDiscussion(input: { repositoryId: $repoId, categoryId: $categoryId, title: $title, body: $body }) {
    discussion { url }
  }
}' \
  -f repoId="$NM_REPO_ID" \
  -f categoryId="$NM_CAT_ID" \
  -f title="[Workflow] <observation title>" \
  -f body="<observation body>"

**If no observations**, skip this step silently.

> **Key distinction**: Repo-specific learnings (code, bugs, > architecture) stay in the current repo as issues or docs. > Tooling learnings (skill/agent/command/hook behavior) always > go to https://github.com/athola/claude-night-market/discussions > so the night-market framework can improve.

Record Lessons Learned (decision journal)

If this PR-fix work involved rework, a failed approach, or a blocker, record it to `docs/lessons-learned.md` so the insight survives past the session (draft and confirm):

  • If leyline is installed, invoke `Skill(leyline:decision-journal)`

and append a lesson entry (`what_happened`, `what_didnt_work`, `root_cause`, `action`; set `phase` to `execute`). Show the draft; append on confirmation.

  • Fallback (leyline absent): append to `docs/lessons-learned.md`

using the in-file ENTRY TEMPLATE; assign the next `LL-NNN` id.

---

> **Back to**: [Main Workflow](../workflow-steps.md)

Read more
Ships withclaude-night-market

A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.

Get the whole plugin, auto-invoked
Stats
325
Stars
0
Views
35
Forks
Active
Maintenance
Python
Language
MIT
License
1d ago
Last commit
8mo ago
Created

Repo: athola/claude-night-market