summarize

A skill that creates a Markdown summary of the current coding session, including changes, decisions, tests, and follow-up work.

In plain words
What is it for?
Use it after a task or plan phase to document changed files, reasons for the changes, tools used, lessons learned, and test results.
Why use it?
It records what happened in a work session and updates the project's context, so completed work is easier to review and continue later.

Skill for Claude CodeCodex

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 skills/brian-lai/para-programming-plugin/summarize
Any agent
npx skills add brian-lai/para-programming-plugin --skill summarize
Clone the repo
git clone --depth 1 https://github.com/brian-lai/para-programming-plugin

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 630 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 $0.00013 $0.00630
Opus 5 $0.00006 $0.00315
Sonnet 5 $0.00003 $0.00126
Haiku 4.5 $0.00001 $0.00063

Measured 2d ago against content hash b433b72447b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarize 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.

skills/summarize/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a summary document from the current work session. Supports both simple and phased plans.

Usage

/para:summarize                   # Auto-detect active plan/phase
/para:summarize --phase=N         # Summarize specific phase

What It Does

  1. Reads worktree_path from context/context.md JSON metadata
  2. Analyzes git changes from the worktree using git -C {worktree_path} diff main...HEAD and git -C {worktree_path} log main..HEAD
  3. Reviews the active plan (or phase) from context/context.md
  4. Creates summary in the main working tree: context/summaries/YYYY-MM-DD-task-name-summary.md (or ...-phase-N-summary.md)
  5. Updates context/context.md: moves plan from active_context to completed_summaries, updates timestamp
  6. For phased plans, marks phase status as "completed"

Summary Sections

  • Date & Status -- when completed, success/failure
  • Changes Made -- files modified/created with line references (from worktree diff)
  • Rationale -- why these changes were made
  • MCP Tools Used -- preprocessing tools utilized
  • Key Learnings -- insights, follow-up tasks, gotchas
  • Test Results -- pass/fail status, coverage metrics

Implementation

  1. Get current date in YYYY-MM-DD format
  2. Read context/context.md to find active plan and worktree_path
  3. If worktree_path is set, analyze changes with:
    • git -C {worktree_path} diff main...HEAD for file-level changes
    • git -C {worktree_path} log main..HEAD --oneline for commit history
  4. If no worktree_path (legacy or --no-worktree execution), fall back to git diff and git status on current branch
  5. Extract task name from plan filename
  6. Create summary file in main working tree with template from summary-template.md
  7. Update context/context.md metadata
  8. Display summary location

Post-Summarize Guidance

If /para:summarize was run standalone (not as part of /para:workflow), the next steps are:

  1. Push the branch: git -C {worktree_path} push -u origin para/{task-name}
  2. Create a PR: gh pr create from the worktree branch
  3. Run /para:archive to clean up the worktree and archive context

Read the full file on GitHub · 56 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 56 lines · 13 tokens per session scan A b433b72447b0

Subscribe to this mod's changes

summarize is a skill published in the GitHub repository brian-lai/para-programming-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 630 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

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

ljg-learn

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…

lijigang/ljg-skills · 113 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

creating-skills

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…

redai-infra/Relax · 70 tokens

grid-ctf-ops

Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.

greyhaven-ai/autocontext · 42 tokens