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 aldianriski/lean-flow --skill diagnosegit clone --depth 1 https://github.com/aldianriski/lean-flowWrote 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/aldianriski/lean-flow/diagnose)<a href="https://agentmods.dev/skills/aldianriski/lean-flow/diagnose"><img src="https://agentmods.dev/badge/skills/aldianriski/lean-flow/diagnose.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 5.1 | $0.00070 | $0.01593 |
| Opus 5 | $0.00035 | $0.00796 |
| Sonnet 5 | $0.00014 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
diagnose 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.
- Prefer an **automated test** at the seam that reaches the bug; then curl/HTTP, CLI snapshot-diff, headless browser, replay a captured trace, a throwaway harness, fuzz, `git bisect run`, or a differential loop. Full men How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose
A discipline for hard bugs. The rate of feedback is your speed limit — build the loop first. Skip a phase only when you can explicitly justify it.
Redact before you show
Every phase below produces an artifact and then shows it — loop output, a captured trace, a log dump, a replayed payload, a HITL transcript. Those carry auth headers, tokens, connection strings and PII by default, and a debugging session is exactly where they get pasted into a chat, an issue, or a commit message. Redact first, and prefer the mechanism over the reminder:
- Build the loop against environment variables so the credential stays in the environment rather than in the command you show. That removes the whole class; redacting afterwards removes instances.
- Quote only the signal-carrying lines of a captured artifact — never a whole HAR file or log dump.
- Whatever must still be shown gets
<REDACTED>in place of the secret, before it is shown. - If the redacted output is no longer enough to diagnose the bug, say so and ask — never widen what you paste to compensate.
Phase 1 — Build a feedback loop
This is the skill — everything else just consumes the signal. Get a fast, deterministic, agent-runnable pass/fail signal for the bug and you will find the cause. Spend disproportionate effort here; be aggressive, refuse to give up.
- Prefer an automated test at the seam that reaches the bug; then curl/HTTP, CLI snapshot-diff, headless browser, replay a captured trace, a throwaway harness, fuzz,
git bisect run, or a differential loop. Full menu →${CLAUDE_SKILL_DIR}/references/feedback-loops.md. - Iterate on the loop — faster, sharper signal, more deterministic. A 2-second deterministic loop beats a 30-second flaky one.
- Non-deterministic bug? Raise the reproduction rate (loop 100×, parallelise, stress), don't chase a clean one-shot repro.
- Genuinely can't build one? Stop, list what you tried, ask for env access / a captured artifact / instrumentation permission. Do not hypothesise without a loop.
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 · 95 lines · 70 tokens per session scan A b2b48a0d615e
diagnose is a skill published in the GitHub repository aldianriski/lean-flow (5 stars, last pushed 9d ago), licensed MIT. It adds 70 tokens to every session and 1,593 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.