go-systematic-debugging

go-systematic-debugging is a skill for Claude Code, Codex from Dankosik/go-service-template-rest. It costs 44 tokens per session (547 once invoked), scanned A, original, MIT.

A guide for diagnosing bugs, flaky tests, build failures, hangs, deadlocks, timeouts, and regressions by tracing the first incorrect condition.

In plain words
What is it for?
Reproducing a failure, testing possible causes one at a time, and identifying the first broken rule in the system.
Why use it?
It keeps debugging focused on evidence and the earliest cause instead of stopping at a later symptom or guess.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Reproducing a failure, testing possible causes one at a time, and identifying the first broken rule in the system.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dankosik/go-service-template-rest/go-systematic-debugging
Install

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.

Any agent
npx skills add Dankosik/go-service-template-rest --skill go-systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/Dankosik/go-service-template-rest

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for go-systematic-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/dankosik/go-service-template-rest/go-systematic-debugging.svg)](https://agentmods.dev/skills/dankosik/go-service-template-rest/go-systematic-debugging)
Your own site
<a href="https://agentmods.dev/skills/dankosik/go-service-template-rest/go-systematic-debugging"><img src="https://agentmods.dev/badge/skills/dankosik/go-service-template-rest/go-systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00547
Opus 5 $0.00022 $0.00273
Sonnet 5 $0.00009 $0.00109
Haiku 4.5 $0.00004 $0.00055

Measured today against content hash 97b3d6cf6757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

go-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 today.

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.

.agents/skills/go-systematic-debugging/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Systematic Debugging

Debugging ends at the first broken invariant, not at the first plausible explanation. Classify the request as diagnosis_only or fix_authorized.

The active workflow owns diagnostic execution. Inside ledger implementation, stay within Implementation's coding-feedback boundary; a blocker alone does not authorize runtime experiments. During final validation, keep causal repair and its focused rerun together.

Reliable Signal

Establish the smallest reliable signal available for the user's exact symptom. Inspect code and form provisional hypotheses as needed to obtain or refine it. For a local symptom, prefer an agent-runnable reproducer; record what was actually run, its result, and any reproduction limit. For a live incident, capture volatile evidence before restart, signal, rollout, or time can destroy it, and state which side of every boundary the evidence covers.

Keep untested explanations provisional and name missing evidence before making a causal claim.

Causal Loop

Minimize further when it improves causal discrimination or materially reduces rerun cost. Choose an experiment that distinguishes plausible causes; isolate the variable or probe whose effect it measures. Track competing hypotheses when several remain or a handoff needs their history, with the evidence that supports, rejects, or blocks each.

Walk backward through affected boundaries until the earliest invariant whose inputs were valid but whose output was wrong. A downstream victim is not the root cause. Use Integration Boundaries when the far-side contract or runtime locator changes the experiment, and load one matching debugging reference only when its stated pressure does.

In fix_authorized, repair the earliest shared owner and confirm the fix against the original symptom and focused regression proof at the correct seam. Reuse a sufficient existing test; if confirmation cannot run, report that exact gap. In diagnosis_only, make no repository edit.

Read the full file on GitHub · 56 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. today Changed · +2 lines 97b3d6cf6757
  2. yesterday Changed · +5 lines 6946591135a3
  3. 8d ago First seen · 49 lines · 44 tokens per session scan A 48eb1a6bc6c3

Subscribe to this mod's changes

go-systematic-debugging is a skill published in the GitHub repository Dankosik/go-service-template-rest (7 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 547 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 2026-08-31.