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 skills/fall-out-bug/sdp/debugnpx skills add fall-out-bug/sdp --skill debuggit clone --depth 1 https://github.com/fall-out-bug/sdpWhat 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 | $0.00014 | $0.00548 |
| Opus 5 | $0.00007 | $0.00274 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
debug 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@debug - Systematic Debugging
Evidence-based debugging using scientific method. Not "try stuff and see" -- systematic investigation.
EXECUTE THIS NOW
When user invokes @debug "<issue>":
Phase 1: OBSERVE - Gather Facts
Goal: Collect evidence WITHOUT forming hypotheses
Actions:
- Read error messages/logs completely
- Check git diff for recent changes
- Verify environment (Python version, dependencies)
- Check configuration files
- Reproduce the bug consistently
Output: Observation log with timestamps, error messages, environment state
Phase 2: HYPOTHESIZE - Form Theories
Goal: Create testable theories about root cause
Process:
- List ALL possible causes (brainstorm)
- Rank by likelihood (use evidence)
- Select TOP theory to test first
- Define falsification test
Output: Hypothesis list with ranked theories
Phase 3: EXPERIMENT - Test Theories
Goal: Run targeted tests to confirm/deny hypotheses
Actions:
- Design minimal experiment
- Run ONLY the experiment
- Record result objectively
- Move to next hypothesis if denied
Output: Experiment results with pass/fail
Phase 4: CONFIRM - Verify Root Cause
Goal: Confirm root cause and verify fix
Actions:
- Reproduce bug with root cause isolated
- Implement minimal fix
- Verify fix resolves issue
- Add regression test
Output: Root cause report + fix
When to Use
- Tests failing unexpectedly
- Production incidents
- Bug reports with unclear cause
- Performance degradation
- Integration failures
Common Pitfalls
| Pitfall | Problem |
|---|---|
| Skipping observation | Jumping to conclusions |
| Testing multiple things | Can't isolate cause |
| Confirmation bias | Only looking for proving evidence |
| Stopping at first fix | Not understanding WHY it worked |
Exit Criteria
- Root cause identified
- Fix implemented and verified
- Regression test added
See Also
@bugfix- Quality bug fixes (P1/P2)@hotfix- Emergency fixes (P0)@issue- Bug classification and routing
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 · 106 lines · 14 tokens per session scan A 7b69f169b205
debug is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 548 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 skills, from other repositories
typescript-best-practices
Enforces TypeScript best practices and modern patterns.
Unit Test Improver
Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.
Refactor Planner
Creates a safe, step-by-step plan to refactor messy code without breaking existing behavior.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
code-discipline
Coding methodology for production-grade software development. Enforces structured thinking before coding, verifying reality, simplicity, surgical changes, contract awareness, and verifiable success criteria. Use when writing, reviewing, or refactoring code that needs to remain reliable over time, including production…
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.