flag-a-signal

flag-a-signal is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 79 tokens per session (1,206 once invoked), scanned A, original, MIT.

A support-signal filer that turns notable customer conversations into structured bug reports, feature requests, or repeated-question groups.

In plain words
What is it for?
Use it to record bugs with reproduction details, attribute feature requests to customers, and find repeated questions that lack a help article.
Why use it?
It helps separate individual support cases from patterns that need engineering work, product attention, or better documentation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to record bugs with reproduction details, attribute feature requests to customers, and find repeated questions that lack a help article.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/flag-a-signal
Install

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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill flag-a-signal
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for flag-a-signal

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/flag-a-signal/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/flag-a-signal)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/flag-a-signal"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/flag-a-signal/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.

agentmods 80×15 button for flag-a-signal

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/flag-a-signal"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/flag-a-signal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01206
Opus 5 $0.00039 $0.00603
Sonnet 5 $0.00016 $0.00241
Haiku 4.5 $0.00008 $0.00121

Measured 7d ago against content hash bdaf02cb8662, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

flag-a-signal 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.

store/agents/support/.agents/skills/flag-a-signal/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flag a Signal

One skill for every "thread contain signal to file" ask. Branch on signal.

When to use

  • bug - "is this bug? log it" / message contain error messages, stack traces, "used to work, now doesn't," repro steps, or screenshots of broken UI.
  • feature-request - conversation or DM contain feature ask ("can you add X?", "would be great if Y").
  • repeat-question - on weekly cron, or when scan last 30–60 days and cluster of semantically similar incoming questions hit ≥3 with no matching article.

Connections I need

I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

  • Dev tracker (GitHub / Linear / Jira) - draft an issue for confirmed bug candidates. Required for bug if you want me to chain into your tracker.
  • Inbox (Gmail) - source threads for clustering repeat questions. Optional if conversations.json already covers the window.

If you want me to file bug candidates in a tracker I stop and ask you to connect the one you actually use.

Information I need

I read your support context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

  • Product surface - Required. Why I need it: tells me what's in-scope (real bug) vs out-of-scope (third-party). If missing I ask: "What does your product actually cover - share a quick overview or point me at your homepage?"
  • Bug vs feature classification rules - Required. Why I need it: the line between "broken" and "missing" determines where the signal goes. If missing I ask: "When a customer reports something doesn't work, what makes it a bug for you versus a feature request?"
  • Help-center platform - Required for repeat-question. Why I need it: I check existing KB coverage before flagging a cluster as a docs gap. If missing I ask: "Where do your help articles live today - Notion, Intercom, a docs site, or nowhere yet?"

Read the full file on GitHub · 68 lines

Changes

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.

  1. 7d ago First seen · 68 lines · 79 tokens per session scan A bdaf02cb8662

Subscribe to this mod's changes

flag-a-signal is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 1,206 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 2026-09-05.