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.
npx skills add HashLips/agent-skills --skill md-compressorgit clone --depth 1 https://github.com/HashLips/agent-skillsWrote 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.
[](https://agentmods.dev/skills/hashlips/agent-skills/md-compressor)<a href="https://agentmods.dev/skills/hashlips/agent-skills/md-compressor"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/md-compressor/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.
<a href="https://agentmods.dev/skills/hashlips/agent-skills/md-compressor"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/md-compressor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01255 |
| Opus 5.5 | $0.00024 | $0.00502 |
| Sonnet 5.5 | $0.00012 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
md-compressor 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MD Compressor
Shrink Markdown to the smallest workable form for agents. Never edit originals — duplicate first, compress the copy only.
End Goal
The machine must still know what to do after compression — at every level, including extreme.
- Always preserve: actionable requirements, constraints, steps, decisions, numbers, commands, paths (per level rules), and skill triggers (
name, usabledescription). - May be reduced as levels increase: tone, encouragement, examples, edge-case color, and duplicate explanations — some context and “feel” can be lost; that is an expected tradeoff.
- Never acceptable: an agent reading only the compressed copy cannot determine what action to take, what order to do it in, or what must not be violated.
- If executability is at risk: keep the longer form, revert that fragment, or step down one compression level for that line or file.
Heavier compression = fewer tokens, not a different skill. When reporting results, note that heavy / extreme copies may omit nuance but must remain agent-executable.
Non-Negotiable Safety
- Duplicate before compress — copy the target skill folder or MD file; write all compressed output into the copy.
- Source stays intact — do not save compression edits to the original path.
- Confirm target — state source path, copy path, and compression level before editing.
Core Rules
- Facts are immutable — requirements, constraints, numbers, paths, commands, and decisions stay exact.
- Level is explicit — default
lightunless the user asks formedium,heavy, orextreme. - Skill = whole package — compress
SKILL.mdand every.mdunderreferences/in the duplicated folder; copy non-text assets unchanged. - Text only — compress Markdown and plain text; skip binaries, images, and non-text assets.
- No semantic drift — if shortening risks changing meaning or what the agent should do, keep the longer form.
- Agent-executable over minimal — prefer tokens saved only when the compressed copy still answers: what to do, in what order, under what constraints.
- Valid skill output — preserve YAML frontmatter keys (
name,description); keepdescriptiontrigger-clear even when shortened.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/abbreviation-map.md 2.2 KB
- references/compression-levels.md 6.3 KB
- references/compression-workflow.md 4.1 KB
- references/extreme-path-shortening.md 3.8 KB
- references/quality-checklist.md 3.0 KB
- references/safe-copy-workflow.md 2.2 KB
- references/skill-package-handling.md 2.6 KB
- references/symbol-and-punctuation-policy.md 3.0 KB
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.
- 1mo ago First seen · 82 lines · 59 tokens per session scan A 0e977893284e
md-compressor is a skill published in the GitHub repository HashLips/agent-skills (28 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,255 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.