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 Dankosik/go-service-template-rest --skill go-systematic-debugginggit clone --depth 1 https://github.com/Dankosik/go-service-template-restWrote 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/dankosik/go-service-template-rest/go-systematic-debugging)<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>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 | $0.00044 | $0.00547 |
| Opus 5 | $0.00022 | $0.00273 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
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.
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.
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.
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.
- today Changed · +2 lines 97b3d6cf6757
- yesterday Changed · +5 lines 6946591135a3
- 8d ago First seen · 49 lines · 44 tokens per session scan A 48eb1a6bc6c3
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.
Other skills, from other repositories
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
config-loader-helper
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
kessoku-di
Kessoku compile-time DI with parallel initialization for Go. Use when writing or debugging kessoku providers/injectors, enabling async dependencies, migrating from google/wire, or fixing go:generate/codegen issues in Go services.
fix-suggester
Diagnose failures and propose minimal, test-backed fixes with verification and rollback instructions.
explain-error
Explain an error message with optional context.