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/patrickjaja/claude-desktop-extra/commentnpx skills add patrickjaja/claude-desktop-extra --skill commentgit clone --depth 1 https://github.com/patrickjaja/claude-desktop-extraWrote 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/patrickjaja/claude-desktop-extra/comment)<a href="https://agentmods.dev/skills/patrickjaja/claude-desktop-extra/comment"><img src="https://agentmods.dev/badge/skills/patrickjaja/claude-desktop-extra/comment.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 | $0.00070 | $0.01029 |
| Opus 5 | $0.00035 | $0.00515 |
| Sonnet 5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
comment 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment - reply to an issue reporter
Target issue: $ARGUMENTS
Context
- Repo:
patrickjaja/claude-desktop-extra - Latest release: !
gh -R patrickjaja/claude-desktop-extra release list --limit 1 2>/dev/null || echo "(gh not ready)"
Step 1 - read the issue
gh issue view $ARGUMENTS --repo patrickjaja/claude-desktop-extra --json number,title,body,state,labels,comments
Read the whole thread, including earlier comments. Note what the reporter already told us so the ask does not repeat it, and note their distro / DE / session type / GPU, because that decides which command block is useful.
Step 2 - the voice (these are hard rules)
The goal is that the reporter invests a little more time and sends us facts. Everything that does not serve that goal comes out.
- Never attribute the cause to our own patches, even when that is exactly what it was. Describe what changed in the release, not who broke it. No apologies for the bug.
- No transparency theatre. No "we tried to reproduce it in four variants and could not", no ranked hypotheses, no internals, no speculation about their hardware. If we do not know, we ask - we do not narrate the search.
- Do not correct the reporter's diagnosis unless they need the correction to collect the right data. It reads as pushback and costs goodwill for nothing.
- One fenced command block, copy-pasteable, no placeholders they have to fill in.
- At most one question, and it must be the highest-value one. Bold it so it does not get lost.
- Short. Target under 200 words of prose. If a paragraph explains our reasoning rather than their next action, delete it.
- Regular dashes only (
-), never em-dashes. Project-wide rule. - No promises about timelines or about what we will fix next.
- Thank them, assume good faith, never imply they should have known something.
Step 3 - the shape
- One line of thanks, specific if possible ("the log excerpt was useful").
- What shipped, if anything: 1 to 3 bullets, each phrased as an observable behaviour change, with the version in bold.
- The ask: "Could you upgrade to X, reproduce it once, and send us the output of:" plus the single command block.
- One sentence on what that output tells us, so it does not feel like busywork.
- Optionally one bolded question.
- Short closing thanks.
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.
- 4d ago First seen · 76 lines · 70 tokens per session scan A 9986379a07dc
comment is a skill published in the GitHub repository patrickjaja/claude-desktop-extra (615 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,029 once invoked, about $0.0003 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
control-flow
Analyze and design control flows and data structures. Produces compact ASCII tree diagrams showing triggers, call chains, payload shapes, state mutations, and re-render effects. Use when user asks to diagram, trace, visualize, or design a flow or data structure.
triage-reviews
Fetch PR review comments, verify each against real code/docs, fix valid issues, commit and push.
assets-get-data
Get asset data from the asset file in the Unity project — every serializable field and property. Supports token-saving path-scoped reads via paths or viewQuery. Use 'assets-find' to find the asset first.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
assets-create-folder
Create a new folder under a parent folder inside 'Assets/'. The parent path must start with 'Assets/' and every intermediate folder in it must already exist. Refreshes the AssetDatabase at the end and returns the GUID(s) of the created folder(s).
assets-prefab-save
Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.