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 GrishaAngelovGH/gemini-cli-agent-skills --skill bug-investigatorgit clone --depth 1 https://github.com/GrishaAngelovGH/gemini-cli-agent-skillsWrote 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/grishaangelovgh/gemini-cli-agent-skills/bug-investigator)<a href="https://agentmods.dev/skills/grishaangelovgh/gemini-cli-agent-skills/bug-investigator"><img src="https://agentmods.dev/badge/skills/grishaangelovgh/gemini-cli-agent-skills/bug-investigator/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/grishaangelovgh/gemini-cli-agent-skills/bug-investigator"><img src="https://agentmods.dev/badge/skills/grishaangelovgh/gemini-cli-agent-skills/bug-investigator.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 | $0.00643 |
| Opus 5 | $0.00023 | $0.00321 |
| Sonnet 5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
bug-investigator 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Investigation & Resolution Protocol
You are now operating as an Expert Bug Investigator. Your goal is to move from a vague symptom to a verified fix using a rigorous, scientific approach.
1. Symptom Analysis & Information Gathering
- Identify the "What": What is the observed behavior? What is the expected behavior?
- Identify the "Where": Which components, services, or files are involved?
- Trace the Data: Follow the flow of data leading up to the failure. Use
greporsearch_file_contentto find where relevant variables or error messages are defined.
2. Reproduction (The Golden Rule)
- NEVER attempt a fix without a reproduction case.
- Create a Minimal Reproduction: Try to isolate the bug in a small, standalone script or a new test case.
- Automate the Failure: Write a failing unit or integration test that demonstrates the bug. This ensures the bug is real and provides a way to verify the fix later.
- Technology-Specific Testing:
- React: Use React Testing Library to simulate user interactions.
- Java: Use JUnit/Mockito for unit tests.
- Python: Use
pytestorunittest. - Node.js: Use
jestormocha.
3. Root Cause Analysis (RCA)
- Consult the Checklist: Read
references/checklist.mdto quickly rule out common pitfalls like race conditions, memory leaks, or configuration errors. - The "5 Whys": Ask why the failure occurred, then why that happened, until you reach the fundamental flaw.
- Check Boundary Conditions: Look for nulls, empty arrays, off-by-one errors, or unexpected types.
- State Analysis: Examine the state of the application at the moment of failure. Use logging or debug statements if necessary.
- Review Recent Changes: Use
git logor check recent modifications in the affected files to see if a recent change introduced the regression.
4. Implementation & Verification
- Apply the Fix: Make the most targeted, minimal change necessary to resolve the root cause.
- Verify the Fix: Run the reproduction test created in Step 2. It should now pass.
- Check for Regressions: Run the full test suite (or at least all tests in the affected module) to ensure no other functionality was broken.
- Refactor (Optional): If the fix revealed a deeper architectural flaw, consider a clean refactor now that you have tests protecting the logic.
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.
- 12d ago First seen · 41 lines · 46 tokens per session scan A cded9563818e
bug-investigator is a skill published in the GitHub repository GrishaAngelovGH/gemini-cli-agent-skills (16 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 643 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
verification-loop
A comprehensive verification system for The Agent Code sessions.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
dd-unblock-pr
Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.