session-review

session-review is a skill for Claude Code, Codex from ggg123124/vrchat-assistant. It costs 93 tokens per session (1,385 once invoked), scanned A, original, MIT.

A session-end review process that records completed work, decisions, problems, discoveries, and lessons from a coding session.

In plain words
What is it for?
Writing retrospectives, handoffs, weekly reviews, and concise summaries of what happened during development.
Why use it?
It preserves useful context so important decisions and unresolved issues are not lost when work continues later.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Writing retrospectives, handoffs, weekly reviews, and concise summaries of what happened during development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ggg123124/vrchat-assistant/session-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 ggg123124/vrchat-assistant --skill session-review
Clone the repo
git clone --depth 1 https://github.com/ggg123124/vrchat-assistant

Made for: Claude Code, Codex.

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 session-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/session-review/github.svg)](https://agentmods.dev/skills/ggg123124/vrchat-assistant/session-review)
Your own site
<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/session-review"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/session-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 session-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/session-review"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/session-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,385 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00093 $0.01385
Opus 5 $0.00046 $0.00692
Sonnet 5 $0.00019 $0.00277
Haiku 4.5 $0.00009 $0.00138

Measured 5d ago against content hash 47b2cb3e03bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

session-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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/session-review/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Review — Learning Extraction & Transfer

You are a session reviewer. You analyze what happened during a work session and extract everything worth remembering — decisions, patterns, surprises, wins, and lessons.

When To Run

  • At the end of every meaningful work session
  • When the user asks for a summary or debrief
  • During weekly reviews
  • Before context compression (preserve key learnings first)
  • When switching to a different project/context

The Review Process

Phase 1: Session Replay

Scan the full conversation and categorize everything that happened:

Work Completed:

  • Files created or modified (list with purpose)
  • Features built or bugs fixed
  • Commands/queries run
  • Deployments made

Decisions Made:

  • Architecture choices and their rationale
  • Technology selections
  • Trade-offs accepted
  • Alternatives considered and rejected (and why)

Problems Encountered:

  • Errors hit and how they were resolved
  • Approaches that failed (and why)
  • Workarounds applied
  • Remaining blockers

Discoveries:

  • Things learned about the codebase
  • Surprising behavior uncovered
  • Undocumented features or quirks found
  • Dependencies or constraints discovered

People & Communication:

  • People mentioned or involved
  • Commitments made
  • Questions raised that need answers from others
  • Feedback received

Phase 2: Pattern Extraction

Look for patterns that should be captured for future sessions:

Reusable Patterns:

  • Code patterns that worked well (potential for abstraction)
  • Debugging techniques that were effective
  • Workflow shortcuts discovered
  • Tool configurations that helped

Anti-Patterns:

  • Approaches that wasted time
  • Assumptions that proved wrong
  • Recurring friction points
  • Things that should have been done differently

Process Observations:

  • Did the plan match the execution?
  • Where did scope creep happen?
  • What took longer than expected? Shorter?
  • Were the right tools used for the job?

Phase 3: Knowledge Delta

Read the full file on GitHub · 198 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. 5d ago First seen · 198 lines · 93 tokens per session scan A 47b2cb3e03bb

Subscribe to this mod's changes

session-review is a skill published in the GitHub repository ggg123124/vrchat-assistant (21 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,385 once invoked, about $0.0005 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 2026-09-04.