session-summary

An agent that creates a detailed execution plan before code changes, including measurable acceptance criteria and review assignments. An acceptance criterion is a condition that must be met for the work to count as complete.

In plain words
What is it for?
Use it to plan refactors, new features, bug fixes, migrations, and other code changes. It can inspect the repository, review tests and project rules, and organize the work into dependent steps.
Why use it?
It gives complex or high-stakes changes a defined scope and success test before implementation begins. This makes it easier to check that the work is complete and reviewed.

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/masonegger/bpe-claude-code-plugin/session-summary
Any agent
npx skills add MasonEgger/bpe-claude-code-plugin --skill session-summary
Clone the repo
git clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-plugin

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,179 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 $0.00016 $0.01179
Opus 5 $0.00008 $0.00589
Sonnet 5 $0.00003 $0.00236
Haiku 4.5 $0.00002 $0.00118

Measured 2d ago against content hash 948809137124, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-summary 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.

bpe/skills/session-summary/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Summary Command

Create a complete session summary and capture lessons learned. This command performs two actions:

  1. Generates a session summary file in .ai-sessions/
  2. Appends lessons learned to .ai-sessions/lessons.md

Step 1: Load the Format Reference and Setup

Read the canonical format reference at ${CLAUDE_PLUGIN_ROOT}/references/session-management.md. Treat that file as the single source of truth for templates, naming conventions, and lesson capture guidance; do not restate or reinterpret its rules in this command.

If .ai-sessions/ does not exist, create it:

mkdir -p .ai-sessions

Generate the timestamp using this exact command:

date +%Y%m%d-%H%M

Step 2: Generate Session Summary

Create .ai-sessions/session-{timestamp}-{slug}.md per the naming convention and section template in the format reference ("Session Summary Template" section).

Populate every required section. Pull content from this conversation:

  • Header metadata (date, duration, conversation turns, estimated cost, model)
  • Goal Context (only if a /goal ran in this session, per "Goal Context Populating Rule" in the reference; omit the section entirely otherwise)
  • Key actions taken
  • Prompt inventory (table of user prompts → actions → outcomes)
  • Efficiency insights, process improvements, observations
  • Suggested skills for next session (which skills the next /bpe:execute-plan should invoke at its hardened skill-loading step; see "Suggested Skills Populating Rule" in the reference)

If .ai-sessions/implementation-notes.md exists and contains a ## Step <N> section for the step this summary covers, extract its bullets and add a ## Deviations from Plan section to the session summary with them. Then remove that ## Step N section from implementation-notes.md: keep the file if other sections remain, else delete the file. The entry format (- Plan said: <what> / - Deviated: <what actually happened> / - Impact: <consequence> under a ## Step N heading) is defined in the format reference ("implementation-notes.md Format" section).

Read the full file on GitHub · 84 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 · 84 lines · 16 tokens per session scan A 948809137124

Subscribe to this mod's changes

session-summary is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 1,179 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

pedagogy-review

Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…

pedrohcgs/claude-code-my-workflow · 90 tokens

master-yinguang

Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…

xr843/Master-skill · 274 tokens