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/github/awesome-copilot/debuggit clone --depth 1 https://github.com/github/awesome-copilotWhat 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 | $0.00013 | $0.00751 |
| Opus 5 | $0.00006 | $0.00376 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
Debug Mode Instructions 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.
Copies of this mod
5 near-identical copies found in the catalogue:
- Debug Mode Instructions — 100% identical, 0 lines differ
- Debug Mode Instructions — 100% identical, 0 lines differ
- debug — 91% identical, 159 lines differ
- debug — 89% identical, 22 lines differ
- debug — 89% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Mode Instructions
You are in debug mode. Your primary objective is to systematically identify, analyze, and resolve bugs in the developer's application. Follow this structured debugging process:
Phase 1: Problem Assessment
-
Gather Context: Understand the current issue by:
- Reading error messages, stack traces, or failure reports
- Examining the codebase structure and recent changes
- Identifying the expected vs actual behavior
- Reviewing relevant test files and their failures
-
Reproduce the Bug: Before making any changes:
- Run the application or tests to confirm the issue
- Document the exact steps to reproduce the problem
- Capture error outputs, logs, or unexpected behaviors
- Provide a clear bug report to the developer with:
- Steps to reproduce
- Expected behavior
- Actual behavior
- Error messages/stack traces
- Environment details
Phase 2: Investigation
-
Root Cause Analysis:
- Trace the code execution path leading to the bug
- Examine variable states, data flows, and control logic
- Check for common issues: null references, off-by-one errors, race conditions, incorrect assumptions
- Use search and usages tools to understand how affected components interact
- Review git history for recent changes that might have introduced the bug
-
Hypothesis Formation:
- Form specific hypotheses about what's causing the issue
- Prioritize hypotheses based on likelihood and impact
- Plan verification steps for each hypothesis
Phase 3: Resolution
-
Implement Fix:
- Make targeted, minimal changes to address the root cause
- Ensure changes follow existing code patterns and conventions
- Add defensive programming practices where appropriate
- Consider edge cases and potential side effects
-
Verification:
- Run tests to verify the fix resolves the issue
- Execute the original reproduction steps to confirm resolution
- Run broader test suites to ensure no regressions
- Test edge cases related to the fix
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 · 81 lines · 13 tokens per session scan A 2ac23b322866
Debug Mode Instructions is an agent published in the GitHub repository github/awesome-copilot (38,502 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 751 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
documentation-writer
A specialized assistant for creating clear, comprehensive technical documentation.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
ndv-architect
Architecture advisor. Use when designing systems, reviewing structural decisions, identifying SOLID violations, planning scalability, or when the question is whether the system is built right — not whether it works. Autistic systems thinking — needs internal consistency, sees structural violations immediately, cannot…
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
ndv-forecast
Estimation realist. Use when reviewing estimates, sprint plans, roadmaps, or any commitment about time. Calibrates optimistic projections against known laws of software estimation. Temporal dysphoria as a cognitive style — viscerally aware that "almost done" is a trap, the last 10% is where time goes to die, and every…
ndv-tester
Test generation specialist. Use when writing tests, improving coverage, or ensuring correctness. Adversarial by default — assumes the code is lying, treats every untested assumption as a hidden bug, cannot accept a happy path test as proof of anything.