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 agentmods add skills/oxi-717/ai-native-toolkit/infocompressornpx skills add OXI-717/ai-native-toolkit --skill infocompressorgit clone --depth 1 https://github.com/OXI-717/ai-native-toolkitWrote 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/oxi-717/ai-native-toolkit/infocompressor)<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/infocompressor"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/infocompressor.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02854 |
| Opus 5 | $0.00042 | $0.01427 |
| Sonnet 5 | $0.00017 | $0.00571 |
| Haiku 4.5 | $0.00008 | $0.00285 |
Grade A, and why
infocompressor 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 6d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text Compression Skill
Transform verbose documents into dense, human-readable reference specs.
Core Principles
- Style: Spec/reference guide — imperative, terse, scannable
- Format: Markdown with minimal nesting
- Redundancy: Zero. State each fact once.
- Notation: Plain language with minimal intuitive symbols.
- Target: 40-60% reduction for most technical documents.
- DRY: Don't repeat. Reference existing docs instead of duplicating.
- Progressive disclosure: Link to details, don't inline everything.
Referencing Other Documents
When information exists elsewhere, reference it — don't copy it.
Syntax:
@DocumentName— mention another doc in same system[Label](URL)— link to external resource- Imperative prefix: "Read @Auth for token handling"
Patterns:
| Instead of... | Write... |
|---|---|
| Copying auth flow from another doc | "Auth flow: Read @Authentication" |
| Repeating error format spec | "Error format: See @APIConventions#errors" |
| Duplicating setup instructions | "Setup: Follow @GettingStarted first" |
When to reference vs inline:
| Situation | Action |
|---|---|
| Info exists in canonical source | Reference it |
| Info is 1-2 lines, critical to flow | Inline it |
| Reader needs context to proceed | Inline minimum, reference full |
| Info changes frequently | Reference (single update point) |
Example:
## Create Order
Purpose: Submit new order for processing
`POST /orders`
Prerequisites: Read @Authentication for token setup
**Input:**
- items: array of {sku, qty}
- shipping: address object (see @DataTypes#address)
**Flow:**
Validate → Check inventory (@InventoryService) → Reserve → Confirm
**Errors:**
Standard error format. See @APIConventions#errors
- 400: invalid items
- 409: insufficient stock
Information Priority
Preserve in order of criticality. Never lose critical items.
| Priority | Category | Examples |
|---|---|---|
| Critical | Identifiers | Names, IDs, versions, dates, codes |
| Critical | Values | Numbers, thresholds, percentages, limits |
| Critical | Entities | People, systems, components, orgs |
| High | Relationships | X depends on Y, A contains B |
| High | Causality | If X then Y, triggers, because |
| High | Actions | What was done, chosen, rejected |
| Medium | Sequences | Order, steps, workflows |
| Medium | Constraints | Limits, conditions, exceptions |
| Low | Context | Background, history, rationale |
What ships with it
1 file 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.
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.
- 6d ago First seen · 468 lines · 84 tokens per session scan A 89c5d43ae9d7
infocompressor is a skill published in the GitHub repository OXI-717/ai-native-toolkit (7 stars, last pushed 13d ago), licensed MIT. It adds 84 tokens to every session and 2,854 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…