Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/logger/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/logger)<a href="https://agentmods.dev/skills/adrienm7/ergopti/logger"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/logger/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/adrienm7/ergopti/logger"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/logger.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00810 |
| Opus 5.5 | $0.00010 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
logger 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logging
The normative reference is the shared
SPEC.md: it owns
the eight variants, the importance/lifecycle grid, punctuation, and driver
conformance contract. AGENTS.md owns the universal English and fail-fast
rules. This skill covers how to apply and verify that contract in practice.
Log extensively
Under-logging is the default failure. Every meaningful state change, lifecycle event, decision and failure path gets a line. Future debugging depends on it — including yours, tomorrow, from a user's log file with no repro.
Selection heuristic: "would I need this line to diagnose a bug in production?"
Yes → info or above. Only useful during active development → debug/trace/done.
High-frequency events (per keystroke, per frame) → debug only.
The pairing rule is enforced
start ↔ success and trace ↔ done must always come in pairs. This is not
cosmetic: a START with no matching SUCCESS in a log is the primary signal
of a silent failure, and the whole convention exists to make that visible.
tests/meta/infra/logger/test_logger_pairing.ahk checks this. An unpaired lifecycle call
fails the suite.
Practical consequence: if a function can return early between start and
success, every early-return path needs its own terminal log — usually an
error or warn, not a success.
Evidence records are never collapsed
info and debug lines are keyed by their unformatted template, so the
repeat collapser (SPEC § 4.2) folds N lines that share a template into the
first plus a summary that may never reach the file. That is right for status
noise and wrong for data a person is asked to send back (one-click field
checks, probes): use LoggerEvidence(Tag, Msg, Args*) / Logger.evidence(module, msg, ...) for those result records (SPEC § 4.3). It renders as [INFO], is
never deduplicated or collapsed, and exists in the AHK logger, the shared Lua
core, the macOS logger and logger.shim. Do not use it for ordinary status
lines, in a loop, or in place of start/success; do not "fix" a flood by
switching it back to info without moving the data elsewhere.
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 · +13 lines ede091a52956
- 10d ago Changed 7dbfb5cc7e32
- 15d ago First seen · 56 lines · 25 tokens per session scan A d5e465ff9535
logger is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 810 once invoked, about $0.0001 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 2026-10-14.
Other skills, from other repositories
bloat-detector
Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans. Use when codebase feels large or before a release.
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
performance-analysis
Performance analysis, bottleneck detection, and optimization recommendations. Use when profiling slow code or systems, hunting a performance regression, or producing an optimization plan with measurable targets.
performance-optimizer
Analyze and optimize code performance, identify bottlenecks, and suggest improvements.
performance-optimization
Use when performance requirements exist, profiling reveals bottlenecks, or Core Web Vitals need improvement. Do NOT use without evidence — premature optimization adds complexity.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.