skill-condenser

skill-condenser is a skill for Claude Code, Codex from Agentic-Insights/foundry. It costs 35 tokens per session (970 once invoked), scanned A, original, Apache-2.0.

A tool for shortening long SKILL.md instruction files while keeping their structure and key information. It is intended for Agent Skills files, which tell a coding agent how to perform a task.

In plain words
What is it for?
Use it when a SKILL.md file is over 200 lines, uses too much prose, or needs terse refactoring. It performs two or three condensation passes.
Why use it?
Long instruction files are harder to scan and may contain repeated wording. This condenses them into shorter bullets, tables, and sections without changing their intended structure.

Skill for Claude CodeCodex

Part of the copywriter plugin — 3 skills, 1 agent 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/agentic-insights/foundry/skill-condenser
Any agent
npx skills add Agentic-Insights/foundry --skill skill-condenser
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry

Made for: Claude Code, Codex.

Or install copywriter, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

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 skill-condenser

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentic-insights/foundry/skill-condenser.svg)](https://agentmods.dev/skills/agentic-insights/foundry/skill-condenser)
Your own site
<a href="https://agentmods.dev/skills/agentic-insights/foundry/skill-condenser"><img src="https://agentmods.dev/badge/skills/agentic-insights/foundry/skill-condenser.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 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 $0.00035 $0.00970
Opus 5 $0.00017 $0.00485
Sonnet 5 $0.00007 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 4d ago against content hash 86d7813f7bb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-condenser 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 4d 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.

plugins/copywriter/skills/skill-condenser/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Condenser

Compress SKILL.md files using CoD with skill-format awareness. Optimized for 2-3 passes (not 5) since skills are structured, not prose.

When to Use

  • SKILL.md exceeds 200 lines
  • Skill contains prose paragraphs instead of bullets
  • Refactoring verbose documentation to terse style

Process

  1. Read the skill to condense
  2. Run 2-3 iterations of cod-iteration with skill-format context
  3. Each iteration: extract key entities, compress to bullets/tables
  4. Output: condensed skill maintaining structure

Orchestration

Iteration 1: Structure Extraction

Pass to cod-iteration:

iteration: 1
target_words: [current_words * 0.6]
format_context: |
  OUTPUT FORMAT: Agent Skills SKILL.md
  - Use ## headers for sections
  - Bullet lists, not prose paragraphs
  - Tables for comparisons/options
  - Code blocks for commands
  - No filler phrases ("this skill helps you...")

text: [FULL SKILL.MD CONTENT]

Iteration 2: Entity Densification

iteration: 2
target_words: [iteration_1_words]
format_context: |
  SKILL.md TERSE RULES:
  - Each bullet = one fact
  - Combine related bullets with semicolons
  - Remove redundant examples (keep 1 best)
  - Tables compress better than lists for options

text: [ITERATION 1 OUTPUT]
source: [ORIGINAL SKILL.MD]

Iteration 3 (Optional): Final Polish

Only if still >150 lines:

iteration: 3
target_words: [iteration_2_words]
format_context: |
  FINAL PASS:
  - Move detailed content to references/ links
  - Keep only: Quick Start, Core Pattern, Troubleshooting
  - Each section <20 lines

text: [ITERATION 2 OUTPUT]
source: [ORIGINAL SKILL.MD]

Expected Output Format

Each iteration returns:

Missing_Entities: "entity1"; "entity2"; "entity3"

Denser_Summary:
---
name: skill-name
description: ...
---
# Skill Name
[Condensed content in proper SKILL.md format]

Skill-Specific Entities

When condensing skills, prioritize these entity types:

Entity Type Keep Remove
Commands deploy.py --env prod Verbose explanations
Options Table row Paragraph per option
Errors Error → Fix Long troubleshooting prose
Examples 1 best example Multiple similar examples
Prerequisites Bullet list Explanation of why needed

Read the full file on GitHub · 150 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. 4d ago First seen · 150 lines · 35 tokens per session scan A 86d7813f7bb3

Subscribe to this mod's changes

skill-condenser is a skill published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 970 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens