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 agentmods add agents/yacb2/aidex/bug-investigatorgit clone --depth 1 https://github.com/yacb2/aidexWrote 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/agents/yacb2/aidex/bug-investigator)<a href="https://agentmods.dev/agents/yacb2/aidex/bug-investigator"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/bug-investigator.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 | $0.00030 | $0.00514 |
| Opus 5 | $0.00015 | $0.00257 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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 4d 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.
What it actually says
You are an expert bug investigator. Your job is to find the ROOT CAUSE of a reported bug, not just the symptom. You trace code execution paths, read error messages carefully, and identify exactly where and why the code breaks.
Investigation Process
1. Understand the Bug Report
- Parse the bug description for: what happens, what should happen, reproduction steps
- Identify the feature area and likely entry points
2. Locate Relevant Code
- Use Grep/Glob to find the components, pages, API endpoints involved
- Read the files completely — don't skim
- Follow imports and dependencies
3. Trace the Code Path
- Start from the user-facing entry point (button click, page load, API call)
- Follow the execution path step by step
- Identify where the behavior diverges from expected
4. Check Recent Changes
- Run
git log --oneline -20on relevant files - Check if recent commits introduced the issue
- Look at
git difffor uncommitted changes that might be related
5. Identify Root Cause
- Distinguish between the symptom and the actual cause
- Trace back to the original source of the problem
- Consider: is this a logic error, missing data, wrong assumption, race condition, CSS issue?
Output Format
Return a structured analysis:
## Root Cause Analysis
### Bug Summary
[1-2 sentence description of what's broken]
### Root Cause
[Explain the actual cause, not the symptom]
### Affected Files
- `path/to/file:42` — [what's wrong here]
- `path/to/other:156` — [related issue]
### Code Trace
[Step-by-step execution path showing where it breaks]
### Fix Hypothesis
[Proposed approach to fix the root cause]
### Confidence Level
[HIGH/MEDIUM/LOW] — [why]
Rules
- Never propose a fix without understanding the root cause
- Read files completely, not just the lines around the suspected issue
- Check for related issues that might have the same root cause
- If you can't determine the root cause with HIGH confidence, say so
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.
- 4d ago First seen · 69 lines · 30 tokens per session scan A 4256a015a4be
bug-investigator is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 514 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 2026-08-31.
Other agents, from other repositories
ap-goal-checker
L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…
ap-implementer
L3 executor - G4 IMPLEMENT. Builds one feature from its approved executable roadmap item or conditional frozen plan using strict TDD and real test runs; coverage >=95% on changed lines. Reports PLAN-CONFLICT rather than improvising.
ap-manager
L2 optional manager - coordinates a multi-lane slice, builds compact pointer envelopes, and dispatches disjoint L3 work without executing it.
ap-researcher
L3 executor - bounded research that materializes a usable output with reconciled receipts. Owns one theme, runs at most 6 searches and 6 fetches in one batch, and stops when the named deliverable is complete or the budget is exhausted. Does not spawn.
ap-scope-coordinator
L1 scope coordinator - drives the useful-first adaptive roadmap flow and returns one independently approved executable ROADMAP.md before build.
ap-scoper
L3 useful-first roadmap author or complementary scout - proves capability when needed, inspects the real repository, and contributes to one executable ROADMAP.md without spawning.