vibe-session-context-flush

vibe-session-context-flush is a skill for Claude Code, Codex from ash1794/vibe-engineering. It costs 38 tokens per session (481 once invoked), scanned A, original, MIT.

A session-management skill that condenses earlier conversation details when the available context is nearly full, while keeping the information needed to continue working.

In plain words
What is it for?
Use it during long sessions with many file reads, before a major new task, or when context compression is approaching.
Why use it?
Long coding sessions can make an agent lose track of important details or become less consistent. It separates active work from completed or irrelevant information and creates a short continuation record.

Skill for Claude CodeCodex

Part of the vibe-engineering plugin — 38 skills shipped together

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/ash1794/vibe-engineering/session-context-flush
Any agent
npx skills add ash1794/vibe-engineering --skill session-context-flush
Clone the repo
git clone --depth 1 https://github.com/ash1794/vibe-engineering

Made for: Claude Code, Codex.

Or install vibe-engineering, the plugin that ships this one along with the rest of its 38 skills.

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 vibe-session-context-flush

README.md
[![agentmods](https://agentmods.dev/badge/skills/ash1794/vibe-engineering/session-context-flush.svg)](https://agentmods.dev/skills/ash1794/vibe-engineering/session-context-flush)
Your own site
<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/session-context-flush"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/session-context-flush.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 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 $0.00038 $0.00481
Opus 5 $0.00019 $0.00241
Sonnet 5 $0.00008 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured 3d ago against content hash b84168a95a4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-session-context-flush 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 3d 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:

plugins/vibe-engineering/skills/session-context-flush/SKILL.md · 62 lines

What it actually says

vibe-session-context-flush

Context windows have limits. This skill manages the transition gracefully instead of letting context degrade silently.

When to Use This Skill

  • You notice responses getting less coherent or losing track of earlier context
  • You've been working for a long session with many file reads
  • The system indicates context compression is occurring
  • Before starting a new major subtask in a long session

When NOT to Use This Skill

  • Short sessions with plenty of context room
  • When the user wants to continue without interruption
  • When you just started the session

Steps

  1. Assess current context — What's consuming context?

    • Large file reads that are no longer relevant
    • Completed subtask details that can be summarized
    • Exploration results that led to dead ends
    • Verbose tool outputs
  2. Triage into:

    • Keep — Still actively needed (current task state, open files, error messages)
    • Summarize — Completed work (compress to 2-3 sentences each)
    • Drop — No longer relevant (old file contents, superseded plans)
  3. Create compact state:

    ## Session State (Flushed)
    **Current task**: [what we're doing]
    **Branch**: [current branch]
    **Modified files**: [list]
    **Completed**: [summary of done work]
    **Key decisions**: [1-liner each]
    **Next step**: [immediate next action]
    **Important context**: [anything that must be preserved]
    
  4. Offer to the user — "Context is getting large. Here's a compact state. Want me to continue with this summary, or start a new session with the handover doc?"

Output Format

Context Flush Summary

Context pressure: High / Medium Items summarized: X Items dropped: Y

[Compact state block as above]

Recommendation: Continue with summary / Start new session with /vibe-handover-doc

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. 3d ago First seen · 62 lines · 38 tokens per session scan A b84168a95a4e

Subscribe to this mod's changes

vibe-session-context-flush is a skill published in the GitHub repository ash1794/vibe-engineering (10 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 481 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.

Related

Other skills, from other repositories

pptgen-drawio

根据论文或汇报内容生成多页 Draw.io 格式 PPT,支持论文答辩与通用汇报两种模式,自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。.

xstongxue/best-skills · 80 tokens

create-skill

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

xstongxue/best-skills · 46 tokens

wechat-article-writer

公众号/自媒体全流程。根据用户表述自动匹配:撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。.

xstongxue/best-skills · 105 tokens

project-docs

对任意代码项目生成一套面向新人的循序渐进文档集,输出到 docs/ 目录。含架构、设计思想、语言特性、代码导读、运行时模型、构建、对接、调试、设计规范共 9 篇,支持全部生成 / 只写几篇 / 更新已有文档。当用户提到"生成项目文档"、"新人文档"、"上手文档"、"架构文档"、"代码导读"、"项目理解"、"深入理解项目"、"onboarding 文档"、"给新同事看的文档"时使用。要按用户给的格式写论文章节、项目梳理、重点问题、简历项目描述的,用 codegen-doc。.

xstongxue/best-skills · 177 tokens

drawio-diagram

为深度学习模型、网络架构、算法流程等生成标准 Draw.io (.drawio) 格式的可视化图表;支持从零生成与风格迁移两种模式。从零生成:模型架构图、流程图、感受野示意图等;风格迁移:参考图 + 内容描述/项目 → 按参考图风格生成新图。确保 XML 格式正确,可直接在 Draw.io 中打开编辑。.

xstongxue/best-skills · 104 tokens

skill-prompt-convert

在 Skill(SKILL.md)与 Prompt(聊天框指令)两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换,保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。.

xstongxue/best-skills · 72 tokens