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 jellydn/my-ai-tools --skill diagnosing-bugsgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/diagnosing-bugs)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/diagnosing-bugs/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/jellydn/my-ai-tools/diagnosing-bugs"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/diagnosing-bugs.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 | $0.00034 | $0.01249 |
| Opus 5.5 | $0.00014 | $0.00500 |
| Sonnet 5.5 | $0.00007 | $0.00250 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
diagnosing-bugs 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.
2. A curl or HTTP script against a running service. How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing Bugs
Use this workflow for bugs, flaky failures, and performance regressions. The central rule is simple: do not start with a theory. First build a feedback loop that can go red on the user's actual symptom.
When to Use
Use when:
- A test, command, request, or UI flow is failing.
- Behavior is incorrect but the failure is not yet understood.
- A bug is intermittent or timing-sensitive.
- A performance regression needs measurement before optimization.
Do not claim a diagnosis from code inspection alone when the symptom has not been reproduced or captured.
Process
1. Redact and gather context
Redact secrets from commands, logs, screenshots, traces, and environment output before showing or storing them. Read the relevant project instructions, glossary, ADRs, issue, and recent changes. Record the exact user-visible symptom, not a nearby error.
2. Build a tight feedback loop
Prefer the smallest unattended command that exercises the real path and asserts the symptom:
- A failing unit, integration, or end-to-end test at the correct public seam.
- A curl or HTTP script against a running service.
- A CLI fixture and expected-output comparison.
- A browser script asserting DOM, console, or network behavior.
- A replay of a captured request, event, or trace.
- A minimal harness with real collaborators at the failing boundary.
- A property or fuzz loop for input-dependent failures.
- A bisection or differential loop when the regression has a known range.
Tighten the loop: cache setup, narrow assertions to the exact symptom, pin time and randomness, isolate the filesystem, and remove unnecessary network work. A slow or flaky loop is not a sufficient feedback loop until it is made deterministic or its reproduction rate is high enough to debug.
If no red-capable loop can be built, stop and report what was tried. Ask for a redacted trace, log, HAR, core dump, screen recording with timestamps, or access to the reproducing environment rather than guessing.
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 Changed · +4 lines c429a420bc37
- 9d ago First seen · 105 lines · 34 tokens per session scan A 546677f6d7f0
diagnosing-bugs is a skill published in the GitHub repository jellydn/my-ai-tools (123 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,249 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
testing-setup
Analyze and create a testing strategy for Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
qa
Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe)…
experiment-iterative-coder
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…
verify
Verification loop — lint -> typecheck -> unit -> integration -> e2e.
check-coverage
Comprehensive assessment of Unit / Integration / E2E three-layer test coverage, identify gaps and provide actionable recommendations.