scholar-mcp: Skill for Claude Code

.agents/skills/logging-standard/SKILL.md

logging-standard is a skill for Claude Code, Codex from pvliesdonk/scholar-mcp. It costs 66 tokens per session (2,614 once invoked), scanned A, a copy of logging-standard, MIT.

A logging guide that defines how the project's Python code records events, errors, and levels using the standard logging library.

In plain words
What is it for?
It helps developers add or change logging calls with the expected logger setup, levels, exception handling, and message format.
Why use it?
Consistent logs make service behaviour and failures easier to inspect without rewriting or hiding messages produced by external frameworks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is pvliesdonk/scholar-mcp's own configuration. It tells Claude Code and Codex how to work on scholar-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scholar-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pvliesdonk/scholar-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pvliesdonk/scholar-mcp/main/.agents/skills/logging-standard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pvliesdonk/scholar-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for logging-standard

README.md
[![agentmods](https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/logging-standard/github.svg)](https://agentmods.dev/skills/pvliesdonk/scholar-mcp/logging-standard)
Your own site
<a href="https://agentmods.dev/skills/pvliesdonk/scholar-mcp/logging-standard"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/logging-standard/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.

agentmods 80×15 button for logging-standard

Your own site · 80×15
<a href="https://agentmods.dev/skills/pvliesdonk/scholar-mcp/logging-standard"><img src="https://agentmods.dev/badge/skills/pvliesdonk/scholar-mcp/logging-standard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.02614
Opus 5.5 $0.00026 $0.01046
Sonnet 5.5 $0.00013 $0.00523
Haiku 4.5 $0.00007 $0.00261

Measured 24d ago against content hash b26b271358e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

logging-standard 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 24d 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.

Origin

This is a copy

94% identical to logging-standard — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/logging-standard/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Logging Standard

Logging Standard

Scope

This standard governs first-party code only — src/scholar_mcp/ and tests/. Two categories of log output are explicitly out of scope; do not try to make them conform, silence them, or reformat them:

  • pvl-core's request-logging middleware: emits conforming event key=value records for every MCP message (request_started / request_completed / request_failed keyed by method=, and the tool_call_* vocabulary carrying tool=<name>). Governed by fastmcp-pvl-core; no first-party code needed.
  • Third-party loggers — uvicorn.access, uvicorn.error, mcp.server.lowlevel.server, httpx, httpcore, docket.worker: configure_logging_from_env governs them for the whole family, and a second rule on the same logger in this repository would only conflict with it. What it does: mcp.server.lowlevel.server, httpx and httpcore sit at WARNING (or the configured level, if stricter) at every level above DEBUG, and at NOTSET under DEBUG so they reappear. uvicorn.access is filtered, not levelled: it stays at NOTSET, only failed requests (status 400 and above) pass below DEBUG, every status passes at DEBUG, and at every level the query string is stripped and a /transfer/<token> segment is redacted — a credential in a request line is not a preference. uvicorn.error is never demoted (it carries bind failures). docket.worker is capped at INFO under DEBUG so its poll loop does not flood the stream.

Framework

  • Standard library logging throughout. Every module: logger = logging.getLogger(__name__).
  • No print() for operational output. No third-party logging libraries; there is no structlog here, and the JSON output below is pvl-core's formatter over ordinary LogRecords.
  • pvl-core's middleware handles tool invocation, timing and error logging automatically.
  • pvl-core owns the root logger. cli._root and make_server() call configure_logging_from_env("SCHOLAR_MCP", verbose=...); it installs the one console handler chain at root, switches FastMCP's own handlers off so fastmcp.* propagates into that chain, and is idempotent (its own handlers are replaced on every call, any other root handler — OTLP, file, syslog — is left alone). Never attach a handler yourself: a second console handler renders every line twice. Everything it writes goes to stderr; stdout is the protocol channel under stdio transport.

Read the full file on GitHub · 175 lines

Changes

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.

  1. 24d ago Changed · +117 lines · +33 tokens per session b26b271358e5
  2. 1mo ago Changed 673facc7c1e5
  3. 1mo ago First seen · 58 lines · 33 tokens per session scan A 4374572e92b8

Subscribe to this mod's changes

logging-standard is a skill published in the GitHub repository pvliesdonk/scholar-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,614 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to logging-standard, differing in 20 lines, and is treated as a copy.

Related

Other skills, from other repositories

triaging-incidents

Creating, triaging, updating, and analyzing ServiceNow incidents, including trend reports. Assess severity, check affected CIs, find related incidents, and recommend assignments. Use when the user mentions incidents, INC numbers, outages, service disruptions, ticket creation, triage, priority, severity, ITSM…

jschuller/mcp-server-servicenow · 89 tokens

xcodebuildmcp-cli

Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

getsentry/XcodeBuildMCP · 48 tokens

triage

Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.

activeing123/mcptoon · 30 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…

comet-ml/opik-mcp · 187 tokens

opik-explain

Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…

comet-ml/opik-mcp · 113 tokens

maintenance

Investigate, adopt, and verify dependency updates. Captures what changed, understands why, cross-references against the codebase, and runs final checks. Supports two entry modes: run the full flow end-to-end, or review updates you already applied.

cyanheads/git-mcp-server · 53 tokens