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 skills add bobmatnyc/claude-mpm-skills --skill systematic-debugginggit clone --depth 1 https://github.com/bobmatnyc/claude-mpm-skillsWrote 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/skills/bobmatnyc/claude-mpm-skills/systematic-debugging)<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/systematic-debugging/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bobmatnyc/claude-mpm-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/bobmatnyc/claude-mpm-skills/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00061 | $0.01162 |
| Opus 5 | $0.00030 | $0.00581 |
| Sonnet 5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
systematic-debugging 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
When to Use
- A bug, error, exception, or crash needs investigation
- Something is "not working" and the cause is unclear
- A test is failing and the reason isn't obvious
- Unexpected behavior needs troubleshooting in any language or framework
Core Workflow
Follow these five phases sequentially. Do not skip ahead to fixing before completing isolation and tracing.
Phase 1: Reproduce
Establish a reliable way to trigger the bug before doing anything else.
- Read the full error message, stack trace, and logs — note exact text, line numbers, and error codes
- Create a minimal reproduction case that triggers the issue consistently
- Record the exact steps, inputs, and environment that cause the failure
Checkpoint: Can you trigger the bug on demand? If intermittent, gather more data before proceeding.
Phase 2: Isolate
Narrow down where the failure originates.
- Use binary search to find the failing component — disable or stub out halves of the system
- Check recent changes with
git log --oneline -20andgit diffagainst the last known good state - Add targeted logging or use a debugger to observe state at key boundaries
# Find which commit introduced the bug
git bisect start
git bisect bad HEAD
git bisect good <last-known-good-commit>
# Git will checkout midpoints — test each one and mark good/bad
Checkpoint: The bug is traced to a specific function, module, or data flow.
Phase 3: Trace to Root Cause
Understand why the failure happens — not just where.
- Read the code path completely from entry point through the failure site
- Check assumptions: what does each function expect vs. what it actually receives?
- Trace data flow backward — where does the bad value originate?
- Verify with evidence: add assertions or print statements to confirm your hypothesis
# Example: verify assumptions about incoming data
def process_order(order):
assert order.status == "pending", f"Expected pending, got {order.status}"
assert order.items, "Order has no items"
# ... rest of processing
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 118 lines · 61 tokens per session scan A 88c1d2d7c6a5
systematic-debugging is a skill published in the GitHub repository bobmatnyc/claude-mpm-skills (75 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,162 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.