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 shaominngqing/flog --skill flog-inspectgit clone --depth 1 https://github.com/shaominngqing/flogWrote 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/shaominngqing/flog/flog-inspect)<a href="https://agentmods.dev/skills/shaominngqing/flog/flog-inspect"><img src="https://agentmods.dev/badge/skills/shaominngqing/flog/flog-inspect/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/shaominngqing/flog/flog-inspect"><img src="https://agentmods.dev/badge/skills/shaominngqing/flog/flog-inspect.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 | $0.00045 | $0.00696 |
| Opus 5 | $0.00023 | $0.00348 |
| Sonnet 5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
flog-inspect scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
7. Use `flog ai curl net#42` when the user asks how to reproduce a request. How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flog Inspect
Use the flog ai CLI. Do not reimplement the flog wire protocol.
When Triggered
Users may not say "use flog" or name this skill. If they ask you to inspect a Flutter app's current state, logs, HTTP requests, SSE/WebSocket traffic, loading issue, button/page behavior, or screenshot-worthy UI problem, use this workflow proactively.
If device/app selection is ambiguous, first run the smallest snapshot without guessing. If it reports multiple apps, rerun with --device and/or --app from the error's next actions.
Workflow
- Decide if the request is visual. If the user mentions page, screen, UI, loading, button, layout, or current state, include
--screenshot. - Start small: run
flog ai snapshot --format json --last 20 --net-last 20. Add--screenshotfor visual requests. - If
ok=false, explainerror.code,message, andnext_actions. - If
ok=true, inspectsummary,notable,logs,network, andscreenshot. - If the snapshot is not enough, narrow first:
- Logs:
flog ai logs --level error --last 20,flog ai logs --tag Auth --last 20, orflog ai logs --search timeout --last 20. - Network:
flog ai net --failed --last 20,flog ai net --status 5xx --last 20,flog ai net --method POST --url login --last 20, orflog ai net --slow 1000ms --last 20.
- Logs:
- Use
flog ai get <id> --detailonly after choosing a stable id from snapshot/list output. - Use
flog ai curl net#42when the user asks how to reproduce a request. - Do not use
--no-redactunless the user explicitly approves exposing secrets. - Cite stable ids such as
log#188,net#42, andchunk#42.13. - Separate visual observations from log/network conclusions.
Response Pattern
- Lead with what the app is doing now, not with the command output.
- Cite the evidence ids you used.
- Say when data is incomplete, for example no connected app, no failed requests, replay buffer missing an id, or screenshot capture failed.
- Ask the user to reproduce the action only when the current snapshot/list/detail does not contain enough evidence.
What ships with it
1 file 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.
- 8d ago First seen · 50 lines · 45 tokens per session scan A 4c7f22194303
flog-inspect is a skill published in the GitHub repository shaominngqing/flog (4 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 696 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rn-agent-observer
Runtime observability for React Native/Expo apps on Android. Use when debugging RN UI, performance (FPS, JS blocking), network, re-renders, or runtime errors on a running app — understand the current screen and UI findings, capture screenshots, UI trees, ref snapshots, per-request network, CDP console/heap/CPU…
crash-triage
Using logcat to surface the real "Caused by:" root cause hidden behind a generic UI error, plus app lifecycle tools for reproducing failures. Use when an app crashes, shows a generic error dialog, or a task needs to find why a native call failed.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…