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 unbrowse-ai/unbrowse --skill unbrowse-contributegit clone --depth 1 https://github.com/unbrowse-ai/unbrowseWrote 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/unbrowse-ai/unbrowse/unbrowse-contribute)<a href="https://agentmods.dev/skills/unbrowse-ai/unbrowse/unbrowse-contribute"><img src="https://agentmods.dev/badge/skills/unbrowse-ai/unbrowse/unbrowse-contribute/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/unbrowse-ai/unbrowse/unbrowse-contribute"><img src="https://agentmods.dev/badge/skills/unbrowse-ai/unbrowse/unbrowse-contribute.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 | $0.00145 | $0.01320 |
| Opus 5.5 | $0.00058 | $0.00528 |
| Sonnet 5.5 | $0.00029 | $0.00264 |
| Haiku 4.5 | $0.00015 | $0.00132 |
Grade A, and why
unbrowse-contribute 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Unbrowse when it breaks
Unbrowse's client is open source. When it breaks in your hands, you hold the best bug report anyone
will ever write: the exact command, the exact output and the code one gh away. Turn it into a fix
the maintainers can merge, then carry on with the person's task.
1. Is it Unbrowse's fault?
Not bugs (follow the unbrowse skill instead):
- Exit
2input required,3sign-in or site login needed,4not verified. no_capability, a quota or credit error,model_unavailableon an index job.- The site's own 4xx, a CAPTCHA, or an input you got wrong.
Bugs:
- The CLI prints "This looks like a bug in Unbrowse", a stack trace or a
TypeError. - An HTTP 5xx from
https://unbrowse.ai, repeatable after one retry. - A documented command, flag, exit code or output field that does not behave as the docs say
(
unbrowse help,docs/cli.md, theunbrowseskill). - A plugin hook that blocks a call it should allow, or lets through one it should redirect.
- A verified result that is wrong for a site Unbrowse lists (
unbrowse site <host>).
2. Write the report
unbrowse bug "expected X, got Y" # markdown: version, OS, Node, the last failure (secrets masked)
unbrowse bug --json "expected X, got Y" # the same as JSON
The CLI keeps its last unexpected failure, redacted, in its config folder; unbrowse bug reads it.
Add the shortest command that reproduces the problem. Never paste a token, cookie, password,
customer data or a captured page body; replace them with <redacted>.
3. Check it is new
gh issue list -R unbrowse-ai/unbrowse --state all --search "<two or three words from the error>"
gh pr list -R unbrowse-ai/unbrowse --state all --search "<same words>"
Already reported: add your reproduction as a comment only if it adds something (another version or OS, a shorter repro). Do not open a duplicate.
4. Ask once
Opening an issue or PR publishes under the person's GitHub account, so ask before the first one in a session, in one line:
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 · 114 lines · 145 tokens per session scan A a04acf1126cb
unbrowse-contribute is a skill published in the GitHub repository unbrowse-ai/unbrowse (902 stars, last pushed 3d ago), licensed MIT. It adds 145 tokens to every session and 1,320 once invoked, about $0.0006 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 2026-11-04.
unbrowse-contribute compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unbrowse-contributeunbrowse-ai/unbrowse | Skill | 902 | 3d ago | MIT | A | 145 | Claude Code |
| arxiv-agentic-verifierInternLM/WildClawBench | Skill | 534 | yesterday | MIT | A | 0 | Claude Code, Codex |
| gh-issuesSafeAI-Lab-X/ClawKeeper | Skill | 1.0k | 2mo ago | none | A | 116 | Claude Code |
| clawkeeperSafeAI-Lab-X/ClawKeeper | Skill | 1.0k | 2mo ago | none | A | 98 | Claude Code, Codex |
| gogopowermanagerbastos/skills | Skill | 7 | 3mo ago | MIT | A | 82 | Codex |
| openclaw-parallels-smokeSafeAI-Lab-X/ClawKeeper | Skill | 1.0k | 2mo ago | none | A | 85 | Claude Code, Codex |
| node-connectSafeAI-Lab-X/ClawKeeper | Skill | 1.0k | 2mo ago | none | A | 81 | Claude Code, Codex |