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.
git clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/commands/skyfox675/agents-skills/gh-issue-use-browser)<a href="https://agentmods.dev/commands/skyfox675/agents-skills/gh-issue-use-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-use-browser/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/commands/skyfox675/agents-skills/gh-issue-use-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-use-browser.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 | $0.00088 | $0.00879 |
| Opus 5 | $0.00044 | $0.00439 |
| Sonnet 5 | $0.00018 | $0.00176 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
gh-issue-use-browser 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- jira-issue-use-browser — 88% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gh-issue-use-browser — file a groomed GitHub issue with a live-browser diagnosis
Arguments: $ARGUMENTS — parsed exactly like /gh-issue (see gh-issue.md in this commands directory): breadcrumb first, optional model:/effort: tokens anywhere, the rest is the description. The filing flow — codebase recon, duplicate check, groomed anatomy, labels, report — is /gh-issue's, unchanged. This command adds one phase: a browser deep-dive run between recon and drafting. Typing this command IS the operator's consent to act in their authenticated browser session for diagnosis. (Tracking work in Jira instead? Use /jira-issue-use-browser.)
The browser deep-dive
Run the browser-diagnosis skill. It reproduces and root-causes the symptom with whichever browser MCP is connected — Chrome (claude-in-chrome), Playwright, Cypress, or Chrome DevTools — and if none is available it falls back to operator-run repro steps. The skill owns the protocol: context/tab isolation, careful-user mutation rules, the dialog hazard, token/cookie redaction, the rabbit-hole guard, and the method (reproduce → trace the failing request via a fetch/XHR shim → mock to isolate → record a repro). The Chrome and Playwright tools are pre-approved above; if you run the Cypress or DevTools MCP, allowlist its tools in .claude/settings.json.
If the dive is substantial, dispatch it as the diagnostician agent (read-only, its own context) running that skill — its deliverable is findings, not code.
Evidence into the issue
Browser findings go in the evidence section alongside the file:line pointers: the failing request/response pair (redacted), console errors with timestamps, the repro steps as a numbered list exactly as performed, screenshots or the recording path, which environment/account the session was signed into, and which browser MCP produced the evidence. Separate "what the client sent" from "what the server returned" — that boundary usually IS the diagnosis. Any leftover test data goes in a "Residue" 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.
- 9d ago First seen · 22 lines · 88 tokens per session scan A 094fbcb51e93
gh-issue-use-browser is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 879 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 2026-08-31.
Other commands, from other repositories
firefox-publish
Lints, signs and uploads a build on the listed or unlisted channel, then walks the user through the review workflow. TRIGGER WHEN: publishing, releasing, submitting, uploading or signing a Firefox extension, or preparing an addons.mozilla.org (AMO) submission.
spec-dogfood
Run autonomous diff-scoped browser dogfood QA for a branch or PR.
feature-video
Record a video walkthrough of a feature and add it to the PR description.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…