stagewise: Skill for Claude Code

.agents/skills/history-compression/SKILL.md

history-compression is a skill for Claude Code, Codex from stagewise-io/stagewise. It costs 74 tokens per session (2,182 once invoked), scanned A, original, AGPL-3.0.

A technical guide to stagewise's system for shortening an agent's conversation history while preserving useful context. It covers how compression boundaries are selected, how recent information is weighted, and how compressions are tested with SQLite.

In plain words
What is it for?
Use it when debugging or extending history compression, tuning its behavior, investigating context-window overflow, or replaying compression tests.
Why use it?
Long agent conversations can exceed the model's context limit. This guide helps developers understand and investigate how history is compressed before that happens.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is stagewise-io/stagewise's own configuration. It tells Claude Code and Codex how to work on stagewise itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stagewise configures →

About the project

stagewise is an open-source agentic IDE that combines a coding agent, browser-based app previews, debugging tools, and git workflows in one development environment. Developers use it to build and inspect applications with models from different providers. Catalogue add-ons extend the IDE's agent workflows.

stagewise-io/stagewise · 6,810 stars · on GitHub · stagewise.io

Reuse

Borrowing it

Nothing to install: this file belongs to stagewise-io/stagewise. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stagewise-io/stagewise/main/.agents/skills/history-compression/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stagewise-io/stagewise

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 history-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/stagewise-io/stagewise/history-compression/github.svg)](https://agentmods.dev/skills/stagewise-io/stagewise/history-compression)
Your own site
<a href="https://agentmods.dev/skills/stagewise-io/stagewise/history-compression"><img src="https://agentmods.dev/badge/skills/stagewise-io/stagewise/history-compression/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 history-compression

Your own site · 80×15
<a href="https://agentmods.dev/skills/stagewise-io/stagewise/history-compression"><img src="https://agentmods.dev/badge/skills/stagewise-io/stagewise/history-compression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,182 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 116
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 117
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin unknown 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 $0.00074 $0.02182
Opus 5 $0.00037 $0.01091
Sonnet 5 $0.00015 $0.00436
Haiku 4.5 $0.00007 $0.00218

Measured 11d ago against content hash c5725ca6d22a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

history-compression 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 11d 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.

.agents/skills/history-compression/SKILL.md · 142 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 11d ago First seen · 142 lines · 74 tokens per session scan A c5725ca6d22a

Subscribe to this mod's changes

history-compression is a skill published in the GitHub repository stagewise-io/stagewise (6,810 stars, last pushed today), licensed AGPL-3.0. It adds 74 tokens to every session and 2,182 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

distill-session-knowledge

Offline-mine this project's pi session JSONL logs into reusable, verified knowledge: extracts faults, decisions, corrections, procedures and docs, promotes only recurring patterns, and routes artifacts into skillmanage, memory and docs. Use on "mine my sessions", "distill session knowledge", "extract lessons from…

BlackBeltTechnology/pi-agent-dashboard · 78 tokens

a2wave-memory

Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.

LilithGames/a2wave · 29 tokens

growmos

Use the repository's living knowledge graph (growmos, in .growmos/) as shared memory. Trigger when the user asks about how parts of the codebase relate, why a decision was made, who owns what, what depends on what; when you finish a meaningful piece of development and should record it; when growmos next reports…

codician-team/growmos · 97 tokens

remember

Save durable facts to nui persistent memory (/.nui/memory/) when the user asks.

plmbr/nui · 20 tokens

always-on-agent-architecture

Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across…

curiositech/windags-skills · 170 tokens

always-on-agent-inputs

How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually…

curiositech/windags-skills · 154 tokens