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 chipfighter/coding-discipline --skill systematic-debugginggit clone --depth 1 https://github.com/chipfighter/coding-disciplineWrote 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/chipfighter/coding-discipline/systematic-debugging)<a href="https://agentmods.dev/skills/chipfighter/coding-discipline/systematic-debugging"><img src="https://agentmods.dev/badge/skills/chipfighter/coding-discipline/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/chipfighter/coding-discipline/systematic-debugging"><img src="https://agentmods.dev/badge/skills/chipfighter/coding-discipline/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 | $0.00092 | $0.00852 |
| Opus 5.5 | $0.00037 | $0.00341 |
| Sonnet 5.5 | $0.00018 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hard rule: do not package a guess as a permanent fix before locating the root cause. If the user explicitly needs emergency containment, you may apply a reversible temporary mitigation first, but you must state its risks and that the root cause is not fixed, then continue investigating.
1. Reproduce
- Read the error message and full stack trace carefully—the answer is often there. Do not skip them. Note the line number, file, and error code.
- Establish a reliable reproduction first: which steps trigger it every time? If you cannot reproduce it reliably, gather data before proceeding. Do not guess.
- Inspect recent changes: git diff, recent commits, new dependencies, and configuration or environment differences.
2. Trace backward to the root cause
- Follow the bad value backward: where did it come from → who called something with it → continue to the source. Fix it at the source, not at the symptom.
- In a multi-component system (CI→build→signing, API→service→library), record what enters and leaves each boundary. Run it once to see which layer fails, then investigate that layer. Do not guess based on intuition.
- Find a similar working example and list every difference from the broken one. Do not assume that "this difference cannot matter."
- Example: an amount on a page has two extra decimal places. Trace it backward: the display layer receives the wrong value → it came from the API → the value read from the database is correct → the API returned cents as dollars. Fix the API layer; do not compensate with display formatting.
3. One hypothesis at a time
- Write it down: "I believe the root cause is X because Y."
- Test it with the smallest change, varying only one thing at a time. Do not stack new fixes on an unverified one.
- If you do not understand X, say so. Do not pretend and guess.
4. Fix the root + add a regression test
- Write a failing test that reproduces the bug before fixing it (see tdd).
- Make one fix in one place. Do not opportunistically refactor or change anything else.
- Verify that the test passes, nothing else broke, and the problem is actually gone (see verify-before-done).
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 · 41 lines · 92 tokens per session scan A e6a6ca5a05b1
systematic-debugging is a skill published in the GitHub repository chipfighter/coding-discipline (24 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 852 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ccc-systematic-debugging
Root-cause debugging under one law: no fix without a confirmed root cause. Reproduce, compare, hypothesize, then fix once with a failing test first. Use when investigating a bug, a failing or flaky test, or an error of unknown cause.
ccc-doctor
Paste-ready Commander health report: install mode, installed vs latest version, clone and cache state, settings, MCP servers, plugin validate and details, mods, Codex doctor, optional source drift checks. Use when Commander misbehaves, after an update, or before filing a support issue.
performance-profiler
Tier: POWERFUL Category: Engineering Domain: Performance Engineering.
advisor-strategy
Use when facing complex architectural decisions, debugging dead-ends, high-stakes code changes, security reviews, performance optimization, or when the user explicitly requests advisor consultation. Also use when context is growing large and needs management, or when a second opinion from a more capable model would…
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eleven checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
investigate
Systematic root-cause debugging: find the cause before writing any fix.