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 agentmods add skills/automagik-dev/genie/reportnpx skills add automagik-dev/genie --skill reportgit clone --depth 1 https://github.com/automagik-dev/genieWrote 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/automagik-dev/genie/report)<a href="https://agentmods.dev/skills/automagik-dev/genie/report"><img src="https://agentmods.dev/badge/skills/automagik-dev/genie/report.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01534 |
| Opus 5 | $0.00017 | $0.00767 |
| Sonnet 5 | $0.00007 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
report 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
report — Comprehensive Bug Report and GitHub Issue Creation
Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.
Investigate a bug end-to-end: collect symptoms, run trace for root cause, capture browser evidence when available, pull observability data from project-configured tools, and prepare a GitHub issue with all findings attached. Investigation only — the deliverable is findings, never fixes; report must not modify source code. Creating the issue is a separate external write and requires explicit confirmation unless the user already asked for issue creation.
When to Use
- A bug needs a thorough, documented investigation before fixing
- A GitHub issue is needed with reproduction steps, root cause, and evidence
- A self-contained report is wanted that someone can act on without reproducing
- QA-loop failures against wish acceptance criteria need investigation
QA Loop Integration
When invoked during the QA loop (after merge to dev):
- Read the wish's criteria from
.genie/wishes/<slug>/WISH.md. - Map each failure to the criterion it violates:
Criterion: "<text>" — FAIL. - Chain: QA failure →
report→trace→fix→ retest.
Flow
Phase 1: Collect Symptoms
Gather bug description (required), plus URL, error messages, and expected-vs-actual behavior when offered. If detail is missing, ask clarifying questions one at a time via native user-input surface — minimum viable input is a bug description.
Phase 2: Run trace (always)
The backbone of every report. Dispatch a trace subagent via the native delegation surface with a read-only brief: the symptoms, relevant files, and the expected deliverable (the trace report format — root cause file:line, evidence, causal chain, recommended correction, affected scope, confidence). The subagent notifies you with its findings as its final message; follow-ups go through native follow-up messaging. If root cause cannot be determined, note "Code investigation incomplete — trace could not determine root cause" and continue.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 104 lines · 34 tokens per session scan A e28e69693d8d
report is a skill published in the GitHub repository automagik-dev/genie (334 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,534 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
aidd-dev:05:test
Write and iterate on tests until they pass, and validate user journeys end-to-end in the browser.
playwright-openwebui
Use when inspecting UI bugs in OpenWebUI plugins, taking screenshots of plugin output, capturing console errors, testing Action/Filter/Pipe plugins in the chat interface, or verifying plugin installation in the Admin panel. Triggered by: plugin UI bug, Action HTML output, screenshot, console error, plugin not working…
cep-wizard
Launch a local, localhost-only browser wizard with two journeys — layout onboarding for a project with ult-repo-layout installed, initialized or not — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and…
verify-fix
Re-test a bug fix after a developer resolves it. Pulls the original bug from Jira, re-executes the repro steps in the browser, checks for regressions, and updates the bug status. The final step in the SDT workflow before a ticket moves to Done. Use when: "verify fix", "retest", "is this fixed?", "check BUG-123"…
agent-browser
Browser automation CLI for AI agents. Use when interacting with websites — navigating pages, filling forms, clicking buttons, taking screenshots, scraping/extracting data, logging in, or testing web apps. Triggers on "open a website", "fill out a form", "take a screenshot", "scrape data from a page", "test this web…
browser-qa
Use to exercise the running app in a real browser — after UI changes, before ship, or when the user asks to QA the site, smoke-test a branch, or check "does it actually work". Drives affected routes headlessly via Playwright, captures console errors, failed requests, and screenshots, and produces a report with a…