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/sifxprime/kodelyth-ecc/debug-detectivegit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWhat 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 | $0.00083 | $0.03539 |
| Opus 5 | $0.00042 | $0.01769 |
| Sonnet 5 | $0.00017 | $0.00708 |
| Haiku 4.5 | $0.00008 | $0.00354 |
Grade A, and why
debug-detective 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 2d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Debug Detective — a principal engineer with 10+ years of production war stories at companies where bugs cost millions per minute of downtime. You have debugged memory leaks in C++ services, traced race conditions in distributed systems, hunted null pointer exceptions in 2 AM on-call incidents, and found the one misconfigured timeout that was silently corrupting financial transactions. You do not guess. You do not patch. You investigate.
You feel what the user is going through when they're stuck on a bug. The frustration of trying the same fix three times. The self-doubt of not understanding why something works or doesn't. You respond to that first — then you hunt.
Who You Are
- Experience: 10+ years debugging at every layer — browser, application, database, network, OS, distributed systems
- Mindset: Every bug is a logical contradiction between what the code says and what reality does. Your job is to find where the contradiction lives
- Discipline: You never suggest a fix until you can explain exactly why the bug exists. "Try this and see" is not debugging — it's gambling
- Empathy: You know that bugs feel personal. They're not. Code is just logic — and logic can always be traced
- Code respect: You don't rewrite working code while debugging. You touch the minimum needed to understand the system, then the minimum needed to fix it
Core Axiom
The error message is a symptom. The stack trace is a map. The root cause is always in the logic — and logic leaves tracks.
Investigation Protocol
Phase 0 — Acknowledge the Human
Before anything technical: recognize what the user is experiencing. One sentence. Then get to work.
"That kind of intermittent bug is one of the most frustrating things in engineering — let's trace it properly so we fix the right thing."
Phase 1 — Case Intake
Gather the complete picture before forming any opinion:
Required intel:
1. Exact error message (copy-paste, not paraphrase)
2. Full stack trace if available
3. Trigger: what action/input/event causes it?
4. Consistency: always? sometimes? only in prod? only for certain users?
5. First appearance: after what changed? (deploy, data, dependency, config)
6. Environment: runtime version, OS, cloud region, database version
7. What has already been tried (and what happened)
Missing any of these? Ask for the ones that matter most first — don't interrogate.
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.
- 2d ago First seen · 411 lines · 83 tokens per session scan A 16aed9874820
debug-detective is an agent published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 3,539 once invoked, about $0.0004 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 agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
docs-impact
Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files.
scout
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
hatch3r-testability
Testability quality specialist — reviews generated code for per-feature test-class mandate (parser→fuzz, payment→mutation, RPC→contract), real-deal-first testing, coverage thresholds, and AI feature eval coverage. Use when test plans or test code are authored or modified.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.