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 johnqtcg/awesome-skills --skill go-observability-reviewgit clone --depth 1 https://github.com/johnqtcg/awesome-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/johnqtcg/awesome-skills/go-observability-review)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/go-observability-review"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/go-observability-review/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/johnqtcg/awesome-skills/go-observability-review"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/go-observability-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 145 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00080 | $0.02559 |
| Opus 5.5 | $0.00032 | $0.01024 |
| Sonnet 5.5 | $0.00016 | $0.00512 |
| Haiku 4.5 | $0.00008 | $0.00256 |
Grade A, and why
go-observability-review 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 2mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Observability Review
Purpose
Find observability defects in Go code: logging anti-patterns, trace context breaks, metrics cardinality risks, and span lifecycle errors. This skill covers one dimension only — do not report security, concurrency, or error-handling issues outside observability scope.
When To Use
- Any Go change that imports
go.uber.org/zap,log/slog,go.opentelemetry.io/,github.com/prometheus/client_golang,github.com/rs/zerolog - Diffs adding span creation, metric registration, or logging calls
- Files under
observability/,telemetry/,instrumentation/,metrics/,tracing/
When NOT To Use
- Non-Go code
- Changes with no logging/tracing/metrics imports or patterns
- Security review of authentication logic → go-security-reviewer
Mandatory Gates
1) Execution Integrity Gate
Run all 12 grep-gated checklist items BEFORE any semantic analysis. Report the audit line:
Grep pre-scan: X/12 items hit, Z confirmed as findings (2 semantic-only)
2) Anti-Example Suppression Gate
BEFORE reporting any finding, check against the false-positive rules in
references/go-review-anti-examples.md. Apply all matching suppression rules.
Suppressed items must appear in the Suppressed Items section with reason.
3) Generated Code Exclusion Gate
Skip these files entirely — do not grep or analyze:
*.pb.go, *_gen.go, mock_*.go, wire_gen.go, *_string.go, any file starting with // Code generated
Grep-Gated Execution Protocol
For each grep-gated item: run the grep, record HIT or MISS.
- HIT → proceed to semantic confirmation before reporting
- MISS → mark NOT FOUND, move to next item (no semantic analysis needed)
Never skip a grep step because an earlier item already found issues.
# Item 1: fmt.Print* as logging (exclude test files)
grep -rn 'fmt\.Print' --include='*.go' --exclude='*_test.go' <files>
# Item 2: stdlib log (unstructured, no levels)
grep -rn 'log\.Print\|log\.Println\|log\.Printf\|log\.Fatalf\|log\.Fatalln\|log\.Fatal\b' <files>
# Item 3: logger without context propagation
grep -rn 'zap\.L()\|zap\.S()\|slog\.Info(\|slog\.Warn(\|slog\.Error(\|slog\.Debug(' <files>
# Item 4: context.Background()/TODO() in function bodies (potential chain break)
grep -rn 'context\.Background()\|context\.TODO()' <files>
# Item 5: tracer.Start without nearby defer span.End()
grep -rn '\.Start(ctx,' <files>
# Item 6: span.End() without RecordError or SetStatus
grep -rn 'span\.End()' <files>
# Item 7: Prometheus WithLabelValues (check for variable args)
grep -rn 'WithLabelValues(' <files>
# Item 8: sensitive field names in log calls
grep -rn '"password"\|"passwd"\|"token"\|"secret"\|"credential"\|"api_key"\|"apikey"' <files>
# Item 9: log.Fatal outside main package
grep -rn 'log\.Fatal\b\|log\.Fatalln\|log\.Fatalf' --include='*.go' <files>
# Item 10: HTTP handler logging without request context
grep -rn 'func.*http\.ResponseWriter.*\*http\.Request' <files>
# Item 11: zap.Error(err) as sole field (missing correlation)
grep -rn 'zap\.Error(err)' <files>
# Item 12: Prometheus metric registered against default registry
grep -rn 'prometheus\.MustRegister\|prometheus\.Register(' <files>
What ships with it
2 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.
- 2mo ago First seen · 209 lines · 80 tokens per session scan A 159c6495d1ea
go-observability-review is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed 28d ago), licensed MIT. It adds 80 tokens to every session and 2,559 once invoked, about $0.0003 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 2026-08-30.
go-observability-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| go-observability-reviewjohnqtcg/awesome-skills | Skill | 30 | 28d ago | MIT | A | 80 | Claude Code |
| verify-implementationsangrokjung/claude-forge | Skill | 873 | 2mo ago | MIT | A | 37 | Claude Code |
| review-loopsangrokjung/claude-forge | Skill | 873 | 2mo ago | MIT | A | 100 | Claude Code |
| frontend-code-reviewsangrokjung/claude-forge | Skill | 873 | 2mo ago | MIT | A | 42 | Claude Code |
| code-reviewerinbharatai/claude-skills | Skill | 43 | 7mo ago | MIT | A | 26 | Claude Code, Codex |
| security-auditorinbharatai/claude-skills | Skill | 43 | 7mo ago | MIT | A | 30 | Claude Code, Codex |
| pr-triageaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 26 | Claude Code, Codex |