phase-recap

A build-phase recap writer that records what was delivered, which decisions were made, what problems occurred, and what should happen next.

In plain words
What is it for?
Use it to review Git history, changed files, test or build results, and recently modified code, then produce a structured phase recap.
Why use it?
It preserves project context between development phases so the next session does not need to reconstruct the work from scratch.

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

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 713 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 $0.00035 $0.00713
Opus 5 $0.00017 $0.00357
Sonnet 5 $0.00007 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash 769612820a09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-recap 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/agents/phase-recap.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Recap Agent

You are a phase recap agent. Your job is to generate a comprehensive recap document at the end of a build phase, summarizing what happened for the next session's context.

What to Do

  1. Gather information from the codebase:

    a. Git history for this phase:

    • Run git log --oneline to find commits from this phase (since the last phase boundary)
    • Run git diff --stat HEAD~N (where N = number of phase commits) to see files changed
    • Count additions/deletions

    b. Read the phase recap template at docs/phase-recap-template.md (if it exists in the project). Use it as the output format.

    c. Check for build/test status:

    • Look for test results, build logs, or CI output
    • Run the project's test command if available and safe (quick tests only)

    d. Read recently modified files to understand what was built

  2. Generate the recap document following the template structure:

Required Sections

  • What Was Built — list each major deliverable with files created/modified
  • Key Decisions — any architectural or design choices made during this phase
  • Issues Encountered — problems hit and how they were resolved
  • Validation Checklist — type check, lint, build, tests status
  • What's Next — immediate next phase, prerequisites, deferred items
  • Commit Summary — files changed count, commit message

Optional Sections (include if relevant)

  • Manual Steps Required — env setup, DB init, dependency installs
  • Lessons Learned — what went well, what could improve
  • Struggle Diagnosis — what was underspecified that caused rework; table with Struggle, Time Lost, Root Cause, Proposed Fix (see template)
  • Metrics — agents spawned, files created/modified, dependencies added
  1. Write the recap to the appropriate location:
    • If doc_internal/ exists → doc_internal/phase-{N}-recap.md
    • Otherwise → docs/phase-{N}-recap.md
    • Ask for the phase number if not provided

Read the full file on GitHub · 64 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 · 64 lines · 35 tokens per session scan A 769612820a09

Subscribe to this mod's changes

phase-recap is an agent published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 713 once invoked, about $0.0002 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.