phase-review

phase-review is a skill for Claude Code from joris887/exosuit. It costs 25 tokens per session (1,170 once invoked), scanned A, original, MIT.

A project review workflow for finishing one development phase and deciding what to build next. It checks completed work, revisits assumptions and decisions, and uses project records to guide the next phase.

In plain words
What is it for?
Use it to review completed features, walk through review stories, refresh research, create review documents, and plan the next phase after approval.
Why use it?
It brings scattered project notes and unfinished stories together before new work begins. This helps reveal changes in direction or planning that are needed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 hooks shipped together

Good fit Use it to review completed features, walk through review stories, refresh research, create review documents, and plan the next phase after approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joris887/exosuit/phase-review
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.

Any agent
npx skills add joris887/exosuit --skill phase-review
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for phase-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/joris887/exosuit/phase-review/github.svg)](https://agentmods.dev/skills/joris887/exosuit/phase-review)
Your own site
<a href="https://agentmods.dev/skills/joris887/exosuit/phase-review"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/phase-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for phase-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/joris887/exosuit/phase-review"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/phase-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.01170
Opus 5 $0.00013 $0.00585
Sonnet 5 $0.00005 $0.00234
Haiku 4.5 $0.00003 $0.00117

Measured 8d ago against content hash b7e461e3a5ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

phase-review 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 8d 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.

.claude/skills/phase-review/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.


phase-review

Running Phase Transition Review for phase: $ARGUMENTS

Process Flow

START → Load context (ASSUMPTION_REGISTER, DECISION_LOG, BACKLOG_INDEX, progress.md)
  → Identify completed epics
  → Walk through Phase Transition Stories (E0N-001 → E0N-006) interactively
  → Generate outputs to docs/reviews/ and vision/
  → If user approves next phase: invoke /ideate with new vision
  → DONE

1. Load Context

Read these files (skip any that don't exist with a warning):

  • docs/reference/ASSUMPTION_REGISTER.md — assumptions to validate
  • docs/reference/DECISION_LOG.md — decisions to review
  • docs/reference/BACKLOG_INDEX.md — epic completion status
  • docs/progress.md — sprint history and metrics
  • vision/project-pitch.md — original vision and No-Gos
  • vision/classification.md — archetype and scale

Determine which phase we're reviewing from $ARGUMENTS or by counting completed review epics.

2. Identify Completed Work

Read epic files from docs/reference/backlog/ to determine:

  • Which epics are complete (all stories done)?
  • Which stories were carried over?
  • What was the overall delivery rate?

3. Execute Phase Transition Stories

Walk through each story interactively. Read .claude/skills/discover/references/phase-transition-template.md for the full story definitions.

3A. Feature Walkthrough (E0N-001)

Walk through every built feature with the user. Copy template from .claude/skills/discover/assets/phase-walkthrough.md to docs/reviews/phase-N-walkthrough.md and fill it in.

3B. Assumption Validation (E0N-002)

Go through ASSUMPTION_REGISTER.md. For each HIGH-impact assumption: VALIDATED, INVALIDATED, or STILL UNKNOWN? Update the register.

3C. Research Refresh (E0N-003)

Load archetype from vision/classification.md. Run archetype-specific research from .claude/skills/discover/references/research-protocols.md (RC6 checkpoint). Save to docs/research/phase-N-refresh.md.

Read the full file on GitHub · 112 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. 8d ago First seen · 112 lines · 25 tokens per session scan A b7e461e3a5ed

Subscribe to this mod's changes

phase-review is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 19d ago), licensed MIT. It adds 25 tokens to every session and 1,170 once invoked, about $0.0001 per session on Opus 5. 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 skills, from other repositories

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

linkedin-post

You take a YouTube video transcript and produce a single LinkedIn post draft.

owainlewis/youtube-tutorials · 0 tokens

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-ultimate-guide · 93 tokens

land-and-deploy

Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

FlorianBruniaux/claude-code-ultimate-guide · 24 tokens

orchestrator-lanes

A file-based project-management playbook for a specific Claude Code development orchestrator. It organizes work into lanes, plans, dependency steps, validation phases, and shipping stages.

VKirill/claude-lane-stack · 0 tokens

git-ai-archaeology

Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.

FlorianBruniaux/claude-code-ultimate-guide · 47 tokens