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 hams-ollo/zen-agent-skills --skill systematic-debugginggit clone --depth 1 https://github.com/hams-ollo/zen-agent-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/hams-ollo/zen-agent-skills/systematic-debugging)<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-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/hams-ollo/zen-agent-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/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 | $0.00149 | $0.05108 |
| Opus 5.5 | $0.00060 | $0.02043 |
| Sonnet 5.5 | $0.00030 | $0.01022 |
| Haiku 4.5 | $0.00015 | $0.00511 |
Grade A, and why
systematic-debugging scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
note: fetched with urllib and digested with hashlib on the retrieved date, at 9,465 bytes. The digest pins upstream as of that date; this file is an adaptation and is expected to differ. How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
systematic-debugging
Turn a reported defect into a named cause with the evidence that established it, distinct from the symptom that was reported, and stop there.
This skill is a draft. It ships with no profile and reaches no adopter until it has been used on
a real defect and blessed, per the contribution bar in the target repository's AGENTS.md.
When to use
- A defect, test failure, build failure, or unexpected behavior arrives and nobody has established why it happens.
- A test passes sometimes and fails other times, and somebody is about to call it fixed.
- A failure surfaces in one component and may originate in another.
- An agent working a task in isolation meets a failure its task file does not describe, and needs to tell a defect it introduced from one it uncovered.
- A task file is about to be written about a symptom. This is the step that belongs in between.
When not to use
- You want the defect fixed. This skill does not fix anything, and it will not be talked into it.
The fix is a task, and
fix-batchdispatches it. - You want the regression test written. That is
test-author. This names the observable that test must pin, and stops. - You want the task file written. That is
new-task, which this feeds. - You want to know whether a fix worked. That is
verifier-agent. - You want the code judged. A cause sitting in ugly code is still just the cause;
house-reviewowns quality. - You want to know whether the defect is worth fixing. That is a priority call, it belongs to the author, and it is expressed on the task file rather than here.
- The thing that went wrong is the agent rather than the repository. This diagnoses defects in a repository under work, not misfires of the harness running it. A run that has been confused by its own context is a different problem with a different answer, and pointing this procedure at it produces a confident cause for a defect that is not in the code.
- The cause is already established and agreed. Skip to whichever skill acts on it.
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.
- 7d ago Changed · +7 lines · -60 tokens per session 44af7353ca94
- 1mo ago First seen · 357 lines · 209 tokens per session scan A 9a4fa8bdbcb1
systematic-debugging is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 149 tokens to every session and 5,108 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring-guru
Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
universal-live-check
Universal live-check framework for coding agents. Executes incremental, deterministic validation across all software domains (CLI, backend, frontend, mobile, embedded, libs). Change-type-aware (feat, fix, hotfix, refactor, migrate, docs). Triggers whenever an agent needs to validate code quality, run linting, perform…
tdd-test-engineer
Use for test-first development, regression tests, flaky test debugging, coverage gaps, test strategy, CI failures, or converting bugs into minimal reproducible tests.
formal-methods
Find bugs and verify behavioral properties with TLA+, Lean, and executable models. Use for concurrency, lifecycle, or critical core-logic audits, explicit formal verification requests, and counterexample-driven regression testing.