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/falense/openpaper/improvenpx skills add falense/openpaper --skill improvegit clone --depth 1 https://github.com/falense/openpaperWhat 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 | $0.00107 | $0.00682 |
| Opus 5 | $0.00053 | $0.00341 |
| Sonnet 5 | $0.00021 | $0.00136 |
| Haiku 4.5 | $0.00011 | $0.00068 |
Grade A, and why
improve 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 2d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve
Turn session insights into a trackable GitHub issue. This skill bridges the gap between "we noticed a problem" and "someone will fix it" — every issue it creates links back to where the idea came from so future readers have full context.
Step 1: Gather the improvement
Check the current conversation for a /reflect retrospective or other discussion
about what to improve. If there's a clear reflection with pain points, use that.
If there's no reflection in the conversation, ask the user what they'd like to improve. A single sentence is enough to get started.
If a /reflect produced multiple pain points, ask the user which ones to turn
into issues (they may want one issue, several, or all of them).
Step 2: Build the origin reference
Every issue must trace back to its origin so future readers understand the context. Collect these details:
- Working directory — the repo/project the session was working in
- Date — today's date
- Trigger — what specifically surfaced this (e.g., "reflection after refactoring the fetcher pipeline" or "user noticed flaky test during PR review")
Step 3: Structure the issue
Draft the issue with this structure:
## Problem
What went wrong or what could be better. Be specific — name the files, tools,
or workflows involved.
## Context
Why this matters. What was the user trying to do when this came up.
## Suggested improvement
Concrete next steps. What should change and roughly how.
## Origin
- **Date:** <date>
- **Working directory:** `<path>`
- **Trigger:** <what surfaced this>
Write a concise title (under 70 characters) that captures the improvement, not the session. Good: "Add retry logic to RSS fetcher timeout handling". Bad: "Session reflection issue".
Step 4: Confirm with the user
Show the draft title and body. Ask for confirmation before creating. The user might want to adjust scope, wording, or labels.
Step 5: Create the issue
Use the gh CLI to create the issue in the current repository:
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.
- 2d ago First seen · 94 lines · 107 tokens per session scan A 7a176311be2d
improve is a skill published in the GitHub repository falense/openpaper (15 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 682 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
flask-docs
Flask 3.1.x — routing, templates (Jinja2), blueprints, testing, contexts, signals, CLI, security, deployment.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
good-docs-writing
Writing style guide derived from Modal's documentation voice. Apply when writing or editing docs, guides, tutorials, or technical prose that should read direct, second-person, confident, low-jargon, and example-first. Use to draft new docs in this voice or to revise existing prose toward it.
live-tutorial
Create an annotated MP4 tutorial from real screenshots of a workflow on the owner's computer. Use only when the owner explicitly asks for a tutorial video, not merely when they ask to watch an action happen live.
dg-piagent
Use when working with pi-agent / @earendil-works/pi-coding-agent SDK — 创建 agent、自定义工具、 编写扩展、修改系统提示词、管理会话、配置模型、处理认证、加载 skills/prompts/context files、 实现完全控制模式、或任何需要调用 pi-agent SDK API 的任务时使用。 也用于企业内网接口接入评估：用户给出企业/内网 LLM 接口文档或地址，问「能不能接」「怎么配」时， 按接口核对清单给出接入建议 + models.json 配置初稿。…