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 marcoguillermaz/Tierward --skill systematic-debugginggit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/marcoguillermaz/tierward/systematic-debugging)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/systematic-debugging"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/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/marcoguillermaz/tierward/systematic-debugging"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/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 | $0.00031 | $0.00880 |
| Opus 5.5 | $0.00012 | $0.00352 |
| Sonnet 5.5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
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 14d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Random fixes waste time and introduce new bugs. Quick patches mask root causes.
The Iron Law: complete Phase 1 before proposing any fix. Skipping Phase 1 is not using this skill.
When to use
Any technical issue: test failures, runtime bugs, unexpected output, build errors, integration failures, performance regressions.
Use especially when:
- "One quick fix" seems obvious — that intuition is untested
- You have already tried one fix and it did not work
- The issue appears in a multi-component system (CI → build → sign, API → service → DB)
Phase 1 — Reproduce & read evidence
Before any fix:
-
Read the error message fully. Stack traces, file paths, line numbers, error codes. Do not paraphrase — the text often contains the direct cause.
-
Reproduce consistently. List exact steps that trigger the issue. If not reproducible: add logging or assertions, gather more data, do not guess.
-
Check recent changes. What changed that could cause this? Git diff, new dependencies, config changes, environment differences.
-
In multi-component systems: add a log or assertion at each component boundary. Run once to identify which layer fails, then investigate that layer specifically.
Phase 2 — Pattern analysis
- Find working code similar to what is broken.
- List every difference between working and broken. Do not assume "that can't matter."
- Identify what the broken code depends on: config, state, environment, calling conventions.
Phase 3 — Hypothesize
Write the hypothesis before touching any code:
"The root cause is [X] because [Y]. Prediction: if X is true, then [Z] should also be observable."
Verify the prediction against Phase 1 evidence before proceeding.
* STOP — hypothesis written and verified against evidence. Wait for confirmation before Phase 4. *
Phase 4 — Fix the root cause
- Create a repro case before writing any fix — failing test, minimal script, or manual reproduction recipe. Must exist.
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.
- 14d ago Changed · +1 lines aa105673fbc1
- 1mo ago First seen · 84 lines · 31 tokens per session scan A 38ce85056921
systematic-debugging is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 880 once invoked, about $0.0001 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
diagnose-skill-run
Diagnose a failed or suspicious Runx skill execution from receipts and harness evidence, then propose the smallest bounded improvement without replaying the failed operation.
postmortem-draft
Turn resolved-incident fragments into a traceable postmortem that separates fragment-cited facts from hypotheses, blocks publication while unknowns remain, and keeps the comms send behind a human gate.
ensemble-fix-issue
Lightweight workflow for bug fixes and small issues (Codex skill for /ensemble:fix-issue).
debug
Discipline skill — systematic debugging process. Use when encountering any bug, debug issue, test failure, broken function, or unexpected behavior, before proposing fixes.
qa-cycle
QA + bugfix cycle until it passes.
reverse-engineer
Reverse-engineer a website's internal APIs, encrypted endpoints, WebSocket streams, and obfuscated JavaScript. Activates when the target data isn't in the HTML, when the site uses encrypted CloudFront/CDN payloads, when real-time streaming data is needed, or when the scrape skill's Phase 0-1 finds API calls that are…