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 mezotv/proofdrop --skill attach-review-proofgit clone --depth 1 https://github.com/mezotv/proofdropWrote 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/mezotv/proofdrop/attach-review-proof)<a href="https://agentmods.dev/skills/mezotv/proofdrop/attach-review-proof"><img src="https://agentmods.dev/badge/skills/mezotv/proofdrop/attach-review-proof/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/mezotv/proofdrop/attach-review-proof"><img src="https://agentmods.dev/badge/skills/mezotv/proofdrop/attach-review-proof.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 | $0.00105 | $0.00430 |
| Opus 5.5 | $0.00042 | $0.00172 |
| Sonnet 5.5 | $0.00021 | $0.00086 |
| Haiku 4.5 | $0.00011 | $0.00043 |
Grade A, and why
attach-review-proof 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 1mo 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.
What it actually says
Attach Review Proof
Uploads a local file to the proofdrop-mcp server and returns a temporary presigned URL you can drop into GitHub markdown. Two tools (prefixed by your client, e.g. mcp__proofdrop-mcp__upload_asset):
upload_asset— upload a local file, get back a URL.delete_asset— remove an object by itskey.
Upload
{ "file_path": "screenshots/before.png", "expires_in_seconds": 604800 }
file_path(required) — local path.expires_in_seconds(optional) — URL lifetime. Default86400, max604800(7 days). Use the max for PR-lifetime links.content_type(optional) — inferred from extension; pass"video/mp4"for.mp4(not auto-detected).
Returns { key, url, expiresAt, ... }. Embed url as  (or a [link](url) for video); keep key to delete_asset later. Max ~25 MB.
Watch out
- Public, short-lived only. Anyone with the URL can fetch it. Use ONLY for review artifacts — never secrets, customer data, or private screenshots.
PROOFDROP_API_KEYgates the endpoint, not the URLs. - Upload before writing the PR/issue body so you paste real URLs.
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.
- 1mo ago First seen · 29 lines · 105 tokens per session scan A 5fa46abdf572
attach-review-proof is a skill published in the GitHub repository mezotv/proofdrop (3 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 430 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.