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 Filip-Podstavec/claude-leverage --skill log-structuredgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/filip-podstavec/claude-leverage/log-structured)<a href="https://agentmods.dev/skills/filip-podstavec/claude-leverage/log-structured"><img src="https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/log-structured.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 | $0.00069 | $0.01492 |
| Opus 5 | $0.00034 | $0.00746 |
| Sonnet 5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
log-structured 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 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.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/log-structured
What it does
Helps retrofit a codebase to the structured-logging spec from AGENTS.md:
{"ts":"2026-05-24T12:34:56.789Z","level":"info","trace_id":"a1b2c3","span_id":"4d5e6f","service":"billing","event":"invoice_paid","attrs":{"invoice_id":"inv_789"}}
Walks a target path, finds anti-patterns, and emits a structured report with file:line citations and concrete suggested replacements. Never modifies code — the user decides per-finding.
Anti-patterns flagged
| Pattern | Why it's a problem | Suggested fix |
|---|---|---|
print(...) in production code |
No level, no context, no structure | Replace with logger call |
console.log(...) in production code |
Same; not structured | Replace with structured logger |
logger.X(f"user {id} did {action}") (Python) |
Values baked into message → agent can't grep event=did_action |
Move values to attrs={"user_id": id, "action": action} |
logger.x(`user ${id} did ${action}`) (TS/JS) |
Same | logger.info("user_action", { user_id: id, action }) |
fmt.Printf("user %d ...", id) followed by log.Print |
Same | slog.Info("user_action", "user_id", id) |
Missing trace_id propagation |
Can't reconstruct request flow | Wire context-aware logger (template per lang) |
Logging to stdout in a service that should log structured (e.g., print in Flask handler) |
Operator tooling can't parse | Wire JSON formatter |
Workflow
-
Resolve target. Default
.(whole repo). If$ARGUMENTShas a path, use that. If--lang <name>is given, restrict scan to that language; else auto-detect from file extensions. -
Detect language(s) by file extension. Walk only files matching:
- Python:
*.py(skiptests/,*_test.py,__pycache__) - TypeScript/JavaScript:
*.ts,*.tsx,*.js,*.jsx(skipnode_modules/,dist/,build/,*.test.*,*.spec.*) - Go:
*.go(skip*_test.go,vendor/) - Rust:
*.rs(skiptarget/,tests/)
- Python:
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 First seen · 138 lines · 69 tokens per session scan A e7f58fb3fa5a
log-structured is a skill published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,492 once invoked, about $0.0003 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
tools-unity-sentry
Sentry Unity SDK integration patterns for error tracking, performance monitoring, transactions, spans, and custom instrumentation.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
hyper-debug
Use when encountering a test failure, exception, regression, or unexpected behavior — before proposing fixes. Also when the user invokes /hyperclaude:hyper-debug. Forms hypotheses systematically instead of guess-and-check thrashing.