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 tomzx/agents --skill attach-assetsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/attach-assets)<a href="https://agentmods.dev/skills/tomzx/agents/attach-assets"><img src="https://agentmods.dev/badge/skills/tomzx/agents/attach-assets/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/tomzx/agents/attach-assets"><img src="https://agentmods.dev/badge/skills/tomzx/agents/attach-assets.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00117 | $0.02549 |
| Opus 5.5 | $0.00047 | $0.01020 |
| Sonnet 5.5 | $0.00023 | $0.00510 |
| Haiku 4.5 | $0.00012 | $0.00255 |
Grade A, and why
attach-assets 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 22d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attach Assets
Copies one or more local files onto a dedicated orphan branch in the repository via a throwaway git worktree, then embeds them in a GitHub issue or PR as a comment (default) or appended to the description body.
The files never land on the default branch and never become inline user-attachments, which suits sensitive screenshots, logs, and internal diagrams.
Because the branch is orphan (no shared history with main) and the files are placed through a temporary worktree, the user's working branch and tree are left untouched.
The assets are still in git history on that branch, so they are visible to everyone with read access to the repo and persist until the branch is deleted and history rewritten; do not use this for material that must never enter the repo at all (use signed expiring object-store URLs for that).
Prerequisites
- The command runs inside a working clone of the target repository.
gitwith push access to the repository.ghCLI authenticated with write access, for posting the comment or patching the description body.- Files must be under GitHub's per-file size limit (roughly 100 MB), since they are committed through ordinary git.
- A target issue or PR.
Provide a full GitHub URL for unambiguous parsing, or a bare number with
--pr/--issue(default) using the current repository. - For private repos, the rendered image is visible to collaborators when viewed in the issue or PR, but the raw URL itself requires a token for a direct fetch.
Skill attribution (GitHub)
Before posting the comment or patching the body, read github-post-attribution/SKILL.md and append the Posted with footer for SKILL_DIR = attach-assets to the posted body.
Path scheme
Each upload is written to the orphan branch under a directory named after the issue or PR number. GitHub issues and PRs share one number sequence, so the number alone is unambiguous:
<number>/<filename>
If the same filename is uploaded twice to the same number, the second upload overwrites the first on the branch; give the file a distinct name instead.
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.
- 22d ago Changed · +6 lines 19e7d47cd8da
- 28d ago First seen · 239 lines · 117 tokens per session scan A a2958e7dcd28
attach-assets is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 2,549 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…