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 bdfinst/agentic-dev-team --skill systematic-debugginggit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/systematic-debugging)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/systematic-debugging"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/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/bdfinst/agentic-dev-team/systematic-debugging"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/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 | $0.00073 | $0.01847 |
| Opus 5.5 | $0.00029 | $0.00739 |
| Sonnet 5.5 | $0.00015 | $0.00369 |
| Haiku 4.5 | $0.00007 | $0.00185 |
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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Overview
When LLMs hit failures, they tend to guess at fixes — changing code, re-running, changing more code. This thrashing wastes context and often makes things worse. This skill enforces a four-phase protocol that requires understanding before action. Systematic debugging resolves issues in 15-30 minutes; guess-and-fix typically takes 2-3 hours with a 40% first-attempt success rate vs 95% systematic.
Iron Law
Find root cause before attempting fixes. Symptom fixes are failure. No fixes without root cause investigation first.
Constraints
- Do not change code until you have a root cause hypothesis
- Do not apply more than one fix at a time
- Do not skip the reproduction step — a bug you can't reproduce is a bug you can't verify as fixed
- Do not guess. Investigate.
- After 3+ failed fix attempts, question the architecture — stop patching
The Four Phases
Phase 1: Reproduce
Goal: See the failure with your own eyes (tool output).
- Run the failing test or trigger the error condition
- Read error messages thoroughly — don't skim. Stack traces contain line numbers, file paths, and often the solution.
- Identify the minimal reproduction — strip away everything unrelated
- Determine if the issue is consistent or intermittent
- Gate: paste the reproduction output. If you can't reproduce it, gather more data — don't speculate.
Phase 2: Investigate & Pattern Analysis
Goal: Gather facts and find working reference points.
Investigate (use as many techniques as needed):
- Read the error: Parse the stack trace. What file, line, and function? What's the actual error type?
- Trace the data flow: Follow the input from entry point to failure point. Where does the actual value diverge from the expected value?
- Graph-assisted tracing: prefer CodeGraph/Repowise over hand-walking the codebase to trace the call path from symptom to source — see
knowledge/codegraph-vs-graphify.mdfor tool selection and the fallback contract. - Check recent changes: What changed since this last worked? (
git diff,git log) - Add observation points: Temporary logging or print statements at key points to see actual values
- Multi-component systems: Add diagnostics at each component boundary — log data entering and exiting each layer to find which layer fails
- Bisect: If the failure surface is large, narrow it down by testing midpoints
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.
- 1mo ago First seen · 131 lines · 73 tokens per session scan A 46f036a7fa35
systematic-debugging is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 1,847 once invoked, about $0.0003 per session on Opus 5.5. 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.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
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.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
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.