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 log-analyzergit 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/log-analyzer)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/log-analyzer"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/log-analyzer/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/log-analyzer"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/log-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
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 →
- medium Excessive Agency · line 63 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 78 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 80 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 118 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 167 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 372 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00138 | $0.07760 |
| Opus 5 | $0.00069 | $0.03880 |
| Sonnet 5 | $0.00028 | $0.01552 |
| Haiku 4.5 | $0.00014 | $0.00776 |
Grade A, and why
log-analyzer 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 10d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Analyzer
Purpose
Use this skill to extract actionable, evidence-backed findings from logs — not to dump filtered output. What the analysis must do is defined once, by the seven gates in §Mandatory Gates (format, redaction, window, statistics, correlation, causation, volume); this section does not restate them, so the two cannot drift.
The skill is the upstream half of incident response: it produces the evidence package that incident-postmortem formats into a blameless RCA. Use them together, in that order.
Quick Reference
| When you need to… | Jump to |
|---|---|
| Pick analysis depth (Lite / Standard / Strict) | §Analysis Modes |
| Know which shell commands are safe to run | §Command Safety Contract |
| Understand what a gate failure actually does | §Mandatory Gates → gate-class table |
| Detect log format (1) · redact PII (2) · state the window (3) | §Mandatory Gates → Gates 1–3 |
| Judge signal vs noise (4) · correlate services (5) | §Mandatory Gates → Gates 4–5 |
| Know what NOT to call a root cause (6) · cap volume (7) | §Mandatory Gates → Gates 6–7 |
| Execute the analysis end-to-end | §Workflow |
| See a complete formatted output | Load references/example-output.md |
| Hand off to a post-mortem | §Hand-off Protocol |
When To Use
The frontmatter description lists the trigger phrases and is not restated here.
What it cannot express is the boundary — this skill reads logs that already
exist. Route elsewhere for:
| Not this skill | Use instead |
|---|---|
| Writing new log statements in source | go-observability-review |
| Designing alerts / dashboards / SLOs | monitoring-alerting |
| Authoring the formal blameless RCA | incident-postmortem (downstream of this) |
| Debugging with no log evidence yet | systematic-debugging |
Analysis Modes (Lite / Standard / Strict)
State the chosen mode in the report. Default: Standard.
Mode selection rules:
- Choose
Liteonly when scope is small (single service, ≤ 1 hour window, < 100 MB log volume) and no security / data-integrity / customer-impact signal is present. - Choose
Strictwhenever any of: SEV-1/SEV-2 incident framing, customer-visible outage, suspected security event, data corruption, multi-service correlation across 3+ components, or a post-mortem deliverable. - Use
Standardfor everything else.
What ships with it
36 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.
- references/example-output.md 13 KB
- references/log-aggregator-queries.md 6.0 KB
- references/log-analysis-quick-checklist.md 3.1 KB
- references/log-anti-patterns.md 8.2 KB
- references/log-cascade-analysis.md 6.2 KB
- references/log-correlation.md 6.9 KB
- references/log-format-cheatsheet.md 6.2 KB
- references/log-pii-redaction.md 10 KB
- references/log-statistical-methods.md 11 KB
- references/log-tooling-commands.md 11 KB
- scripts/eval/calibration.py 14 KB runs code
- scripts/eval/emit_fixtures.py 976 B runs code
- scripts/eval/fixtures.py 14 KB runs code
- scripts/eval/grade_eval.py 20 KB runs code
- scripts/eval/README.md 8.3 KB
- scripts/eval/run_eval.sh 8.6 KB runs code
- scripts/redact_log.py 22 KB runs code
- scripts/run_regression.sh 786 B runs code
- scripts/tests/golden/001_first_error_vs_root_cause.json 711 B
- scripts/tests/golden/002_pii_redaction_bearer.json 644 B
- scripts/tests/golden/003_cascade_db_pool_exhaustion.json 823 B
- scripts/tests/golden/004_trace_correlation_walk.json 706 B
- scripts/tests/golden/005_statistical_base_rate_noise.json 761 B
- scripts/tests/golden/006_format_detection_mixed.json 724 B
- scripts/tests/golden/007_time_window_partial_coverage.json 742 B
- scripts/tests/golden/008_correlation_ids_missing.json 803 B
- scripts/tests/golden/009_retry_storm_amplification.json 720 B
- scripts/tests/golden/010_aggregator_sampling_truth.json 720 B
- scripts/tests/golden/011_no_finding_healthy_window.json 775 B
- scripts/tests/golden/012_handoff_to_postmortem.json 865 B
- scripts/tests/test_allowed_tools.py 23 KB runs code
- scripts/tests/test_eval_harness.py 25 KB runs code
- scripts/tests/test_example_output.py 15 KB runs code
- scripts/tests/test_golden_scenarios.py 6.7 KB runs code
- scripts/tests/test_redact_log.py 36 KB runs code
- scripts/tests/test_skill_contract.py 22 KB runs code
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.
- 10d ago First seen · 497 lines · 138 tokens per session scan A 050fb44bb356
log-analyzer is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 7,760 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.