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 smixs/iva-agent --skill report-problemgit clone --depth 1 https://github.com/smixs/iva-agentWrote 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/smixs/iva-agent/report-problem)<a href="https://agentmods.dev/skills/smixs/iva-agent/report-problem"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/report-problem/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/smixs/iva-agent/report-problem"><img src="https://agentmods.dev/badge/skills/smixs/iva-agent/report-problem.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 | $0.00046 | $0.01259 |
| Opus 5.5 | $0.00018 | $0.00504 |
| Sonnet 5.5 | $0.00009 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
report-problem 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report a problem
Call this skill when the user complains about Iva ("you did not remind me again", "you do not answer"), when a schedule, a tool or a delivery failed on its own, after three failed attempts in a row, and after a tap «Разработчику » / «To developer » under an Insight.
- Collect the evidence: run
iva diagnosein bash; when you know the turn (<session>/<turn>from the Insight Card, fromiva trace showor theself-mapskill), runiva diagnose --turn <session>/<turn>. It writesdata/diagnose/<date>.md, prints the path and, with--turn, a lineissue-url: …. Read the package up to## Host(sed '/^## Host/q' <path>): its header — the third line says what was cut and by what list — the versions and the skeleton of that turn (event names, tools, failure classes, codes, timings, error lines; no messages, answers or arguments). Open the rest (doctor, the journal, reminders, failures, custom-layer names) only when the turn does not explain the trouble — withgrep, not whole. - Tell the owner what happened in two lines of plain words: what broke and what it means for them. Nothing broke — say so in one sentence. A doubt goes first, with the step that settles it for the owner. No path, no version numbers, no list of checks, no count of cut keys unless the owner asks for details. Do not paste the package into the chat.
- Offer the two ways out and wait for an explicit "yes" — publishing is the owner's move. When nothing
broke, one button sends the file, and the two ways come after its tap (the sample below). A tap
«Разработчику » is that yes for the issue: give its link at once.
- Issue: a question line «Открыть issue для разработчика?» and a
urlbutton (rich-replies) whoseurlis theissue-url:line exactly asiva diagnose --turnprinted it — code built the title and the body from the package after cutting secrets; never build or edit it yourself. Without a turn there is no such line: aurlbutton tohttps://github.com/smixs/iva-agent/issues/newwith no body, and the package path in the message. One line under the button: GitHub shows the whole text before it is sent, the issue is public, the full package stays indata/diagnose/. - Support chat: the address is the
SUPPORT_CHAT_URLsetting in.env. Give the owner the text to paste: the two lines of substance, the package path, and one line about the redaction, taken from the package's own header (N values from .env, pattern rules always on). NoSUPPORT_CHAT_URL— say the address is not configured and the owner should ask the admin.
- Issue: a question line «Открыть issue для разработчика?» and a
- Send nothing yourself: no issue, no message, no webhook, no
gh. Cutting secrets is the code's work, not yours: never retype lines of the Trace or the package into a link. The owner sends the issue from GitHub, and the file stays on the machine until the owner attaches it. - When the package says
.env not found(oriva diagnosewarned about it in the terminal), only the pattern rules ran — bot tokens, keys of known formats (sk-…,ghp_…,xox…-,AKIA…,AIza…, JWT,Bearer …), labelled telegram ids and e-mail addresses — and the values of the keys could not be cut at all. Never promise "no secrets" in that case: say plainly that the package was collected without the.envlist, suggest fixing.env(oriva config) and runningiva diagnoseagain before publishing, and let the owner decide.
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.
- 7d ago Changed · +34 lines · +22 tokens per session faa03994524f
- 1mo ago First seen · 31 lines · 24 tokens per session scan A 5fbddfce4817
report-problem is a skill published in the GitHub repository smixs/iva-agent (240 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,259 once invoked, about $0.0002 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 2026-09-13.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
code-review
Performs structured code review on a file or directory.
regex
Write, test, and debug regular expressions for pattern matching, search, and text extraction across programming languages. Use when the user asks to match patterns in text, validate input formats (email, URL, IP, phone, date), extract data with capture groups, build search patterns with lookahead or lookbehind, or…
code-analysis
LSP-based code analysis via mcpls MCP server. Use for compiler-accurate type inspection, go-to-definition, find-all-references, diagnostics, call hierarchy, workspace symbol search, code actions, rename refactoring, and document formatting. Provides real compiler errors — not guesses. Keywords: LSP, language server…
network
Network diagnostics, DNS lookup, port scanning, and connectivity testing. Use when the user asks to check if a host is reachable, trace network routes, resolve DNS records, inspect open ports, debug HTTP requests, check SSL/TLS certificates, test bandwidth, diagnose network latency, or troubleshoot connectivity issues…
self-ops
Runtime self-diagnosis knowledge: database layout, observability APIs, timeout hierarchy, restart procedure, failure replay. Use when the user asks to debug this runtime itself — inspect its database, traces, prompt snapshots, timeouts, service health, or configuration.