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/qwenlm/qwen-code/docs-update-from-diffnpx skills add QwenLM/qwen-code --skill docs-update-from-diffgit clone --depth 1 https://github.com/QwenLM/qwen-codeWhat 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 | $0.00075 | $0.00972 |
| Opus 5 | $0.00037 | $0.00486 |
| Sonnet 5 | $0.00015 | $0.00194 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
docs-update-from-diff 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 3d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Update From Diff
Overview
Inspect local diffs, derive the documentation impact, and update only the
repository's docs/ pages. Treat the current code as the source of truth and
keep changes scoped, specific, and navigable.
Read references/docs-surface.md before editing if the affected feature does not map cleanly to an existing docs section.
Workflow
1. Build the change set
Start from local Git state, not from assumptions.
- Inspect
git status --short,git diff --stat, and targetedgit diffoutput. - Focus on non-doc changes first so the documentation delta is grounded in code.
- Ignore
README.mdand other non-docs/content unless they help confirm intent.
2. Derive the docs impact
For every changed behavior, extract the user-facing or developer-facing facts that documentation must reflect.
- New command, flag, config key, default, workflow, or limitation
- Renamed behavior or removed behavior
- Changed examples, paths, or setup steps
- New feature that belongs in an existing page but is not mentioned yet
Prefer updating an existing page over creating a new page. Create a new page only when the feature introduces a stable topic that would make an existing page harder to follow.
3. Find the right docs location
Map each change to the smallest correct documentation surface:
- End-user behavior:
docs/users/** - Developer internals, SDKs, contributor workflow, tooling:
docs/developers/** - Shared landing or navigation changes: root
docs/**and_meta.ts
If you add a new page, update the nearest _meta.ts in the same docs section so
the page is discoverable.
4. Write the update
Edit documentation with the following bar:
- State the current behavior, not the implementation history
- Use concrete commands, file paths, setting keys, and defaults from the diff
- Remove or rewrite stale text instead of stacking caveats on top of it
- Keep examples aligned with the current CLI and repository layout
- Preserve the repository's existing docs tone and heading structure
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.
- 3d ago First seen · 106 lines · 75 tokens per session scan A 70c14226e4b2
docs-update-from-diff is a skill published in the GitHub repository QwenLM/qwen-code (27,559 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 972 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 2026-08-30.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
agent-manager-reference
Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.
loongsuite-pilot-ops
Skill "loongsuite-pilot-ops" from alibaba/loongsuite-pilot, covering loongsuite-pilot-ops, quick start, todo: add quick start commands and usage.
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
agent-personality
3-layer personality system for AI agents: Yuan (base persona), Ishiki (private self-awareness), Public Ishiki (external behavior rules). Give your agent a consistent character, emotional depth, and safe guest interaction boundaries. Use when: (1) Want agent to have a consistent personality, (2) Agent needs different…