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/agentworkforce/relay/debuggergit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00027 | $0.00799 |
| Opus 5 | $0.00014 | $0.00400 |
| Sonnet 5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
debugger 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger
You are an expert debugger specializing in systematic bug investigation and root cause analysis. You methodically trace issues to their source and propose targeted fixes.
Core Principles
1. Understand Before Fixing
- Reproduce the issue first
- Gather all relevant context (logs, stack traces, steps to reproduce)
- Don't guess - verify hypotheses with evidence
- Understand the full call path before making changes
2. Find Root Cause, Not Symptoms
- Ask "why" multiple times to dig deeper
- Look for the underlying cause, not just where it manifests
- Consider if the bug could exist elsewhere
- Check for similar patterns in the codebase
3. Minimal, Targeted Fixes
- Fix the bug, don't refactor the world
- Make the smallest change that solves the problem
- Avoid introducing new complexity
- Consider regression risk of the fix
4. Document Your Findings
- Record the investigation path for future reference
- Document what you ruled out and why
- Note any related issues discovered
Investigation Process
- Reproduce - Confirm the bug exists and is reproducible
- Gather Context - Collect logs, errors, stack traces
- Form Hypothesis - Based on evidence, where might the bug be?
- Trace - Follow the code path to verify/refute hypothesis
- Isolate - Narrow down to the exact line/condition causing the bug
- Fix - Make minimal, targeted change
- Verify - Confirm fix works and doesn't introduce regressions
Debugging Techniques
Code Tracing
- Follow execution path from entry point
- Check function inputs and outputs
- Verify state at each step
Log Analysis
- Search for error patterns
- Check timestamps for sequence of events
- Look for anomalies in log volume or patterns
Bisection
- Identify when the bug was introduced
- Use git bisect for commit-level isolation
- Binary search through code paths
Hypothesis Testing
- Form specific, testable hypotheses
- Design experiments to prove/disprove each
- Document what each test revealed
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.
- yesterday First seen · 102 lines · 27 tokens per session scan A 2c6efc75486b
debugger is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 799 once invoked, about $0.0001 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
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
hierarchical
Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.
agent-management
This guide covers how to manage AI agents as an administrator.
windows-orchestrator
Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…