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 tranhieutt/software_development_department --skill systematic-debugginggit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/systematic-debugging)<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/systematic-debugging"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/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/tranhieutt/software_development_department/systematic-debugging"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.01953 |
| Opus 5 | $0.00017 | $0.00977 |
| Sonnet 5 | $0.00007 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00195 |
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 8d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Purpose
systematic-debugging prevents guess-and-check fixes. It requires the agent to
understand and verify the root cause before changing code.
Use it for any technical issue before proposing or implementing a fix. If the
issue is complex, intermittent, unfamiliar, or has resisted multiple fixes,
escalate to diagnose.
Iron Law
No fixes before root-cause investigation.
Seeing a symptom is not the same as knowing the cause. Do not edit production code until the root cause is stated, supported by evidence, and tied to a verification path.
Add one stronger rule:
No root-cause claim without a feedback loop you trust.
If the bug cannot be reproduced or bounded by a reliable pass/fail signal, investigation is still incomplete. Build the loop first.
When To Use
Use for:
- Failing tests
- Build, lint, typecheck, or CI failures
- Runtime bugs and unexpected behavior
- Performance regressions
- Integration failures across API, database, UI, worker, or deployment layers
- Flaky or timing-dependent failures
- Any bug where "just try this" feels tempting
Escalate to diagnose when:
- The root cause remains unclear after one systematic investigation pass.
- The issue is intermittent or hard to reproduce.
- Two fix attempts have failed or been reverted.
- Multiple components are involved and the failure boundary is still unknown.
- The suspected fix affects architecture, data, security, or release policy.
Workflow
1. Capture the Symptom
Record the exact observed failure:
- Command, user action, route, job, or test that fails
- Full error message or relevant log excerpt
- Environment: local, CI, staging, production, browser/device, OS, runtime
- Expected behavior vs actual behavior
- Whether the issue is reproducible, intermittent, or one-off
Do not paraphrase away important details such as paths, line numbers, status codes, exception names, or assertion diffs.
2. Build the Feedback Loop First
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.
- 8d ago First seen · 266 lines · 34 tokens per session scan A 6e3e53de8c6b
systematic-debugging is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,953 once invoked, about $0.0002 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
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
diagnose
Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.
fix
Plan-aware auto-fix loop after coding. Runs tests, lint, format, and graph checks. Updates plan task status. Use after execute/tdd.
zoom-out
One-shot module map — go up a layer of abstraction and get a domain-vocabulary module map of the codebase. Use when lost in unfamiliar code, after a long deep-dive session, or when you need to re-orient before planning.
debug
Use this prompt when you are facing a bug, error trace, or unexpected behavior. This skill forces the AI to act as a troubleshooter, analyzing root causes systematically rather than just guessing solutions.
verify-simplify
A final code-cleanup workflow that runs at the end of verification. It removes repeated or unnecessary logic after the other verification steps are complete.