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/bendrucker/claude/attachnpx skills add bendrucker/claude --skill attachgit clone --depth 1 https://github.com/bendrucker/claudeWhat 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 | $0.00072 | $0.00793 |
| Opus 5 | $0.00036 | $0.00396 |
| Sonnet 5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
github:attach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attachments
Images and video in issues and pull requests are served from a user-attachments store. POST https://uploads.github.com/user-attachments/assets puts a file there and answers with the URL to reference. It has no REST route and no documentation, so gh api reaches it by full URL.
Upload
repository_id takes the numeric REST id. gh repo view --json id returns the GraphQL node id, which fails here.
repo_id=$(gh api repos/{owner}/{repo} --jq .id)
gh api --method POST \
"https://uploads.github.com/user-attachments/assets?repository_id=$repo_id&name=picker.png&content_type=image/png" \
--input ./picker.png --jq .url
The response is {"url": "https://github.com/user-attachments/assets/<uuid>"}.
The token needs write access to that repository. Read-only access answers 404, which makes a permission problem look like a missing repository.
File Types
The extension in name must agree with content_type, and nothing outside this list uploads. Logs, archives, and PDFs have no path here.
| Extension | content_type |
|---|---|
.png |
image/png |
.jpg, .jpeg |
image/jpeg |
.gif |
image/gif |
.webp |
image/webp |
.svg |
image/svg+xml |
.mp4 |
video/mp4 |
.mov |
video/quicktime |
.webm |
video/webm |
Images cap at 10 MB. Video caps at 100 MB or lower, depending on the account plan.
Reference
An image is ordinary markdown, with \, [, and ] escaped in the alt text.
Video has no markdown syntax. GitHub renders a player when a bare asset URL is the whole of a paragraph.
Ordering
An upload cannot be undone and an asset cannot be deleted. Upload once the body is final and nothing is left that could cancel. An asset nothing references is stranded and permanent, and it answers 404 until something references it, so opening the URL proves nothing about the upload.
The --attach Flag
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 · 73 lines · 72 tokens per session scan A 73d8d5cc1a8e
github:attach is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 793 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.