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 skills add buildinternet/uploads --skill github-screenshotsgit clone --depth 1 https://github.com/buildinternet/uploadsWrote 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/buildinternet/uploads/github-screenshots)<a href="https://agentmods.dev/skills/buildinternet/uploads/github-screenshots"><img src="https://agentmods.dev/badge/skills/buildinternet/uploads/github-screenshots/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/buildinternet/uploads/github-screenshots"><img src="https://agentmods.dev/badge/skills/buildinternet/uploads/github-screenshots.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 74 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 74 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 77 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 78 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 79 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00320 | $0.05452 |
| Opus 5.5 | $0.00128 | $0.02181 |
| Sonnet 5.5 | $0.00064 | $0.01090 |
| Haiku 4.5 | $0.00032 | $0.00545 |
Grade A, and why
github-screenshots scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| A shell and hosted MCP, but no `uploads` binary (cloud sandbox) | Hosted MCP `sign_upload_url` with `files: [{ filename }]` + `repo` + (`pr` or `branch`), then run each returned `curl` line. Each response carries `mark How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshots and recordings in GitHub PRs and issues
Why this exists
GitHub's native image hosting (github.com/user-attachments/…) is reachable
from a browser and, since GitHub CLI 2.99 (September 2026), from
gh issue|pr create|edit|comment --attach <file>. There is still no public REST
endpoint (the CLI uses an undocumented upload host), the upload needs push access, and the hosted file is private to
GitHub. Any other image URL in a PR/issue body written with gh … --body-file
must already point at something publicly hosted. The uploads CLI and the
hosted MCP at https://agents.uploads.sh/mcp both host the file on uploads.sh
and return a stable public URL plus ready-to-paste markdown.
When gh --attach is enough
Use plain gh pr comment --attach ./shot.png (or create/edit) when ALL
of these hold:
gh --versionis 2.99 or newer and you have push access to the repo.- The PR or issue already exists, or you are creating it in the same command.
- The file is an image or video under 10 MB (video up to 100 MB on paid plans).
gh --attachtakes media only. - Nobody needs the link outside GitHub.
user-attachmentsURLs do not render in Slack, docs, or other tools, and other agents cannot fetch them.
Use uploads.sh when any of these are true instead:
- The artifact is not media: a Lighthouse or test report, a log, JSON, a PDF, or
a zip.
gh --attachdoes not take those;uploads putdoes, and the managed comment links them. - The PR does not exist yet. Stage on the branch with
uploads put; the attachments comment appears when the PR opens. - The shot will be re-taken. Same filename, same URL, and the managed comment updates in place instead of piling up.
- The capture needs metadata (
--meta), later retrieval (uploads find), or the Screenshots view across projects. - The URL must work outside GitHub.
- You are on the hosted MCP with no shell, lack push access, or the repo is on GitHub Enterprise Server.
Do not mix the two on one PR: pick one so the comment history stays readable.
Media attached with gh is still indexed: the GitHub App imports attachments
from PR and issue text into the workspace. The same webhook imports public
Cursor cursor.com/artifacts/c/art-* rewrite URLs from that text. To mirror
an existing user-attachments image or art-* URL by hand, use uploads ingest.
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.
- today Changed · +7 lines 31c6ee1e14cf
- 2d ago Changed · +7 lines 75e47360ab8b
- 4d ago Changed · +6 lines 506b57ab5ef0
- 16d ago Changed · +2 lines eff81cdcddc1
- 28d ago Changed · +1 lines ce63851c7bf6
- 29d ago Changed · +2 lines fcbbf76968c0
- 1mo ago Changed · +1 lines fa7e99dae95c
- 1mo ago Changed · +24 lines · +17 tokens per session 11a96b2228c6
- 1mo ago Changed · +40 lines · +25 tokens per session db571649893a
- 1mo ago First seen · 326 lines · 278 tokens per session scan A e7d2dde1c9b1
github-screenshots is a skill published in the GitHub repository buildinternet/uploads (19 stars, last pushed today), licensed Apache-2.0. It adds 320 tokens to every session and 5,452 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
open-pr
Take a cloudflare/agents GitHub issue plus any repro findings and one-shot a fix PR — branch, change, test, push, and open the PR linked to the issue.
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
release-notes
Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
ship
Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'.…