Agent skill

Evanflow Compact

by evanklem in evanklem/evanflow

Manage long-session context to prevent drift and degradation.

Custom licenceAuto-check passedWriting & Content

Install Evanflow Compact

skills CLI
$ npx skills add evanklem/evanflow --skill evanflow-compact -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install evanklem/evanflow evanflow-compact --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/evanklem/evanflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evanflow-compact .claude/skills/evanflow-compact && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
evanflow-compact
GitHub stars
418
Token cost
~1.6k tokens
SKILL.md length
861 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Custom licence

At a glance

Manage long-session context to prevent drift and degradation.

  • Works in 4 steps: Identify anchors: what files, decisions,… → Author a compaction summary in the… → Tell the user: "I'm at a clean boundary.… → …
  • Tasks that involve Summarization
  • SKILL.md covers Vocabulary, When to Use, The Strategies (pick one based… and Drift Symptoms Checklist, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Evanflow Compact is an agent skill from evanklem/evanflow. Manage long-session context to prevent drift and degradation. Strategies for proactive summarization, branch isolation, and /clear decisions. Invoke when context feels heavy, when accuracy starts slipping, or proactively after a major phase boundary. Addresses the

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Summarization. The repository describes itself as: A TDD-driven iterative feedback loop for software development. 16 cohesive Claude Code skills walk an idea from brainstorm → plan → execute → iterate, with checkpoints throughout.

When your agent uses it

  • Tasks that involve Summarization

Example prompts

  • “/evanflow-compact”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Identify anchors: what files, decisions, and open questions must survive? List them explicitly.
  2. Author a compaction summary in the conversation as a markdown block titled ## Phase Summary (compaction anchor). Include
  3. Tell the user: "I'm at a clean boundary. Want me to compact context here? You can /clear and re-orient from this summary + the saved…
  4. If user says yes → they /clear, then start the next phase fresh with the summary in front of them.

What it can do on your machine

Read from SKILL.md and the folder at commit c9ae21f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evanflow Compact loads about 1.6k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 861 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 861 words (~1,601 tokens).

“Why this exists: Context drift kills agents before context limits do. Industry research found ~65% of enterprise AI failures in 2025 traced to context drift or memory loss in multi-step reasoning, NOT raw token exhaustion. The agent's ability to reason…”

— opening of SKILL.md by evanklem, Custom licence
name
evanflow-compact

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/evanflow-compact of evanklem/evanflow.

Open the folder on GitHubat commit c9ae21f

Compare with similar skills

Evanflow Compact next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evanflow Compact compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evanflow Compact this skillevanklem/evanflow418—~1.6kAutomated safety check: PassCustom licence
News Aggregator Skillcclank/news-aggregator-skill1.3k—~2.1kAutomated safety check: PassNone
Vss Search ArchiveNVIDIA-AI-Blueprints/video-search-and-summarization1.9k—~3.6kAutomated safety check: PassApache-2.0
AI Daily Newsgeekjourneyx/ai-daily-skill235—~2.3kAutomated safety check: PassNone
AnalyzeriBigQiang/feedgrab614—~1kAutomated safety check: PassMIT
Reportmicrosoft/data-formulator18k—~1.5kAutomated safety check: PassMIT

Similar skills

  • News Aggregator Skill

    cclank/news-aggregator-skill

    Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR…

    1.3k GitHub stars~2.1k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed
  • Vss Search Archive

    NVIDIA-AI-Blueprints/video-search-and-summarization

    A skill your agent uses when a user wants to search archived VSS video or ingest or delete a source for search.

    1.9k GitHub stars~3.6k tokensUpdated today
    Writing & ContentAuto-check passed
  • AI Daily News

    geekjourneyx/ai-daily-skill

    Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization.

    235 GitHub stars~2.3k tokensUpdated today
    Writing & ContentAuto-check passed
  • Analyzer

    iBigQiang/feedgrab

    Content Analyzer — any content (URL, text, transcript) into structured analysis report with actionable insights.

    614 GitHub stars~1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Report

    microsoft/data-formulator

    Official

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded…

    18k GitHub stars~1.5k tokensUpdated today
    Writing & ContentAuto-check passed
  • Tldr

    earlyaidopters/claudeclaw

    Summarize the current conversation into a TLDR note and save it to your notes folder.

    173 GitHub stars~953 tokensUpdated 5 mo ago
    Writing & ContentAuto-check passed

More from evanklem/evanflow

All 14 skills in this repo
  • Evanflow

    evanklem/evanflow

    Meta skill for the EvanFlow system. An agent skill from evanklem/evanflow.

    418 GitHub stars~2.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Coder Overseer

    evanklem/evanflow

    Orchestrate parallel implementation with coder/overseer pairs.

    418 GitHub stars~3.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Glossary

    evanklem/evanflow

    Extract canonical domain terms into CONTEXT.md. An agent skill from evanklem/evanflow.

    418 GitHub stars~829 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Prd

    evanklem/evanflow

    Synthesize a PRD (Product Requirements Document) for a big new feature.

    418 GitHub stars~817 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow QA

    evanklem/evanflow

    Conversational bug discovery → issue draft. An agent skill from evanklem/evanflow.

    418 GitHub stars~718 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow TDD

    evanklem/evanflow

    Vertical-slice TDD for any production code. An agent skill from evanklem/evanflow.

    418 GitHub stars~2k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Evanflow Compact

What does Evanflow Compact do?

Manage long-session context to prevent drift and degradation. Evanflow Compact is an agent skill from evanklem/evanflow. Manage long-session context to prevent drift and degradation.

When should I use Evanflow Compact?

Evanflow Compact fits situations like: tasks that involve Summarization.

How do I install Evanflow Compact in Claude Code?

Run `npx skills add evanklem/evanflow --skill evanflow-compact -a claude-code`. Or copy the skill folder (skills/evanflow-compact in evanklem/evanflow) into .claude/skills/evanflow-compact in your project. Claude Code loads it when a task matches its description.

How do I install Evanflow Compact in Codex?

Run `npx skills add evanklem/evanflow --skill evanflow-compact -a codex`. Or copy the skill folder (skills/evanflow-compact in evanklem/evanflow) into .agents/skills/evanflow-compact in your project. Codex loads it when a task matches its description.

Can I use Evanflow Compact in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add evanklem/evanflow --skill evanflow-compact -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evanflow-compact, .gemini/skills/evanflow-compact, .github/skills/evanflow-compact and .opencode/skills/evanflow-compact in your project.

What does Evanflow Compact need to run?

SKILL.md names no scripts, command-line tools or credentials: Evanflow Compact is instructions for the agent only.

Does Evanflow Compact access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Evanflow Compact safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Evanflow Compact use?

Evanflow Compact has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Evanflow Compact use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Evanflow Compact?

Skills that share tags, products or a category with Evanflow Compact: News Aggregator Skill (cclank/news-aggregator-skill, 1.3k stars), Vss Search Archive (NVIDIA-AI-Blueprints/video-search-and-summarization, 1.9k stars), AI Daily News (geekjourneyx/ai-daily-skill, 235 stars) and Analyzer (iBigQiang/feedgrab, 614 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evanflow Compact?

evanklem (a GitHub user) maintains it in evanklem/evanflow, which has 418 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on May 13, 2026.

Source: evanklem/evanflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.