condensing-instructions

condensing-instructions is a skill for Claude Code, Codex from jl-cmd/claude-dev-env. It costs 83 tokens per session (883 once invoked), scanned A, original, MIT.

A guide for shortening instruction documents used by Claude 5 generation models. It removes unnecessary rules, resolves conflicts, and moves useful detail to the place where it is needed.

In plain words
What is it for?
It is for refining system prompts, CLAUDE.md files, skills, tool descriptions, and agent instructions.
Why use it?
It reduces instruction clutter and conflicting guidance, making it easier for the model to follow the important decisions.

Skill for Claude CodeCodex

Part of the claude-dev-env plugin — 62 skills, 3 commands, 9 agents, 8 hooks 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/jl-cmd/claude-dev-env/condensing-instructions
Any agent
npx skills add jl-cmd/claude-dev-env --skill condensing-instructions
Clone the repo
git clone --depth 1 https://github.com/jl-cmd/claude-dev-env

Made for: Claude Code, Codex.

Or install claude-dev-env, the plugin that ships this one along with the rest of its 62 skills, 3 commands, 9 agents, 8 hooks.

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 condensing-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/condensing-instructions.svg)](https://agentmods.dev/skills/jl-cmd/claude-dev-env/condensing-instructions)
Your own site
<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/condensing-instructions"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/condensing-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 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 $0.00083 $0.00883
Opus 5 $0.00042 $0.00441
Sonnet 5 $0.00017 $0.00177
Haiku 4.5 $0.00008 $0.00088

Measured 4d ago against content hash 24c96e77b035, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

condensing-instructions 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.

packages/claude-dev-env/.agents/skills-archived/condensing-instructions/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Condensing Instructions

Cut an instruction document to what a Claude 5 generation model needs, and move the rest to the surface that loads it on demand. Over 80% of Claude Code's system prompt came out for Claude Opus 5 and Claude Fable 5 with no measurable drop in performance, so treat a long instruction document as a place with room to cut.

Clear the conflicts first

Read the system prompt, the CLAUDE.md, and the skills as one body of text and find the lines that pull against each other — "leave documentation as appropriate" sitting beside "DO NOT add comments". A conflict makes the model deliberate at length before it acts. Resolve each pair into one statement, or delete both when neither changes what the model does.

Trade rules for judgment

Delete a rule written to block a worst case, such as file deletion. Claude 5 generation models read the surrounding context and decide well without it, and a rigid rule blocks the user who has a real reason to want the behavior it forbids.

State the outcome and the signal the model should read:

  • Cut: "Default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max. Don't create planning, decision, or analysis documents unless the user asks for them."
  • Keep: "Write code that reads like the surrounding code: match its comment density, naming, and idiom."

Design the interface in place of examples

Examples constrain exploration. Carry usage in the tool's own shape: expressive names, expressive parameters, and types that signal intent. A status parameter enumerated as pending, in_progress, completed shows correct use with no example attached.

Load detail at the point of use

Move detail out of always-on text and into a surface the model reaches for:

  • A skill the model calls when the task calls for it. Code review and verification detail belongs here.
  • A linked file the model opens on demand.
  • A tool with deferred loading, where the model searches for the definition before it uses the tool.

Read the full file on GitHub · 73 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 · 73 lines · 83 tokens per session scan A 24c96e77b035

Subscribe to this mod's changes

condensing-instructions is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 883 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 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens