phase-complete

A command that closes a development phase after checking required review and project-alignment steps.

In plain words
What is it for?
Use it to finish a planning or build phase, run its post-phase checklist, and record whether the work is aligned or has documented divergence.
Why use it?
It catches unfinished review work or differences between the planned feature and its original intent before the phase is marked complete.

Command 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 commands/gosha70/code-copilot-team/phase-complete
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

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 837 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 $0.00837
Opus 5 $0.00000 $0.00418
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00084

Measured 2d ago against content hash d3ea7ac15188, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-complete 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.

adapters/claude-code/.claude/commands/phase-complete.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signal phase completion. Validates that the review loop has passed (if peer review is enabled) and runs the post-phase checklist.

Steps

1. Gather Context

Determine from the current session:

  • feature_id — from specs/*/plan.md frontmatter or ask the user
  • phaseplan or build (infer from current work or ask)
  • subject_providerclaude (this session's provider)
  • peer_provider — from CCT_PEER_PROVIDER env var, or empty for profile default
  • review_scope — from CCT_PEER_REVIEW_SCOPE env var, or both
  • target_ref — current git branch or HEAD commit

1.5. Origin Alignment Gate

Run scripts/check-origin-alignment.sh <feature_id>.

  • Exit 0 — aligned, high. Proceed to step 2.
  • Exit 1 — aligned, medium/low, OR partial/derailed with a fresh committed specs/<feature_id>/origin-divergence.md (option C from the skill body — the user has acknowledged the divergence in writing). Proceed with a recorded warning.
  • Exit 2 — partial. Abort. Surface the three-resolution escalation: A) rescope the spec to match the origin, B) restart from origin, C) document the divergence as deliberate (specs/<feature_id>/origin-divergence.md; once committed and newer than the alignment record, the script exits 1 instead). Wait for the user to pick A/B/C. Do not proceed to step 2 until the script returns exit 0 or 1.
  • Exit 3 — derailed. Same as exit 2 but stronger language: the working artifact delivers something fundamentally different from the origin.
  • Exit 4 — missing or stale alignment record. Run the origin_alignment_check procedure from shared/skills/origin-confirmation/SKILL.md to produce a fresh record, then re-run the script.
  • Exit 5 — origin frontmatter missing or malformed. Author must add an origin: block to specs/<feature_id>/plan.md; cannot complete the phase without it.

This gate is independent of peer review (step 2). Peer review scores implementation quality; this gate scores origin alignment.

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A d3ea7ac15188

Subscribe to this mod's changes

phase-complete is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 837 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.