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/jira-issue-use-aws-browser)<a href="https://agentmods.dev/commands/skyfox675/agents-skills/jira-issue-use-aws-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/jira-issue-use-aws-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/jira-issue-use-aws-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/jira-issue-use-aws-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 | $0.00104 | $0.01374 |
| Opus 5 | $0.00052 | $0.00687 |
| Sonnet 5 | $0.00021 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
jira-issue-use-aws-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 11d 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.
This is a copy
91% identical to gh-issue-use-aws-browser — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/jira-issue-use-aws-browser — file a groomed Jira issue with a correlated full-stack diagnosis
Arguments: $ARGUMENTS — parsed exactly like /jira-issue (see jira-issue.md): breadcrumb first, optional model:/effort: tokens anywhere, the rest is the description. The filing flow is /jira-issue's, unchanged. The deep-dive phases and ALL their ground rules come from the two siblings and apply verbatim here:
jira-issue-use-browser.md(the browser-diagnosis skill) — context isolation, careful-user mutation rules, dialog hazard, residue tracking, token/cookie redaction, rabbit-hole guard, on whichever browser MCP is connected (Chrome, Playwright, or Cypress).jira-issue-use-aws.md— identity-first, the read-only verb allowlist,lambda invokeis forbidden, secrets stay sealed, AccessDenied is a finding.
What this command adds is the correlation method — neither side alone finds the faults that live between layers. (Tracking work in GitHub instead? Use /gh-issue-use-aws-browser.)
The correlated dive
Work the stack as one trace, in this order:
-
Codebase recon first (per
/jira-issue): map the breadcrumb to the components, the API operations they call, and the cloud resources behind them. This map tells you what to watch on both sides. -
Reproduce in the browser (per
jira-issue-use-browser): perform the user's steps in your own tab group and capture the failing request — method, URL/operation, payload, status, response body, and above all any request/correlation IDs and the precise timestamp. A fresh repro matters because it generates evidence you can find in logs that are still hot. Record the repro GIF while you're there. -
Chase that exact request through AWS (per
jira-issue-use-aws): take the correlation ID/timestamp into the logs of each hop the recon map predicts — edge (4xx/5xx, WAF, CDN), service (handler logs around the timestamp), then data (does the row/object/queue message the code expects actually exist, with the key shape the code queries?). CloudTrail for config drift when behavior changed without a deploy.
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.
- 11d ago First seen · 37 lines · 104 tokens per session scan A 364e4f0add70
jira-issue-use-aws-browser is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 104 tokens to every session and 1,374 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to gh-issue-use-aws-browser, differing in 22 lines, and is treated as a copy.
Other commands, from other repositories
bug-report
Draft a bug report issue for lean4-skills.
triage
Query open Node bugs, classify by priority and sub-team, suggest assignments, and generate a triage summary.
speckit.companion.doctor
Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).
harvest-errors
Analyze the latest test262 run results, cross-reference with existing issues, and create new issues for unaddressed error patterns.
postmortem
Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.
harness:maintenance-pipeline
On-demand, report-first maintenance sweep — runs overdue checks via harness maintenance run, triages findings, and asks the human in plain text before dispatching any fix.