A procedure for analyzing game-engine and build logs from Unreal, Unity, Godot, or Microsoft build tools. It uses a log-analysis command to summarize, filter, group, and classify messages instead of printing the whole file.

Use it to locate logs, count errors and warnings, search by text or category, and group repeated diagnostics by code or source location.

Large logs can be too noisy and expensive to read directly, making the important errors difficult to find.

logs — Command for coding agents by JSungMin: A procedure for analyzing game-engine and build logs from…

Install

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.

agentmods

npx agentmods add commands/jsungmin/vs-token-safer/logs

Clone the repo

git clone --depth 1 https://github.com/JSungMin/vs-token-safer

Or install gamedev-log-analyzer, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 agent, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/logs.svg)](https://agentmods.dev/commands/jsungmin/vs-token-safer/logs)

Your own site

<a href="https://agentmods.dev/commands/jsungmin/vs-token-safer/logs"><img src="https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/logs.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 752 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5	$0.00064	$0.00752
Opus 5	$0.00032	$0.00376
Sonnet 5	$0.00013	$0.00150
Haiku 4.5	$0.00006	$0.00075

Measured 5d ago against content hash 41695ca4ae0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logs 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

logs — 100% identical, 0 lines differ

gamedev-log-analyzer/commands/logs.md · 42 lines

What it actually says

gamedev-log-analyzer — game-engine/build log analysis

Read the log smartly via the gamedev-log CLI — never cat/grep/Get-Content the raw log (it can be tens of MB). Run it through Bash with the plugin-root path (pure Node, no deps, no PATH setup); quote every path:

node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" <command> [--flags]

Steps:

Locate it: … detect --projectPath "<dir>" (UE Saved/Logs/*.log + Unity Editor.log, newest first). If nothing is found, ask for the log path or persist one with … setup --projectPath/--logPath.
Triage: … summary --path "<log>" for severity counts + top categories.
Search/filter: … search --path "<log>". Useful flags:
- --severityMin Error (errors only) | Warning (default).
- --query <substr> · --category <Cat> (e.g. LogStreaming) · --file <pathfrag>.
- --groupBy callsite rolls up by file:line (best for "which callsite floods the log").
- --groupBy code rolls up by diagnostic code (C4996/LNK2019/CS1002 …) — collapses a noisy build to one line per code (C4996: … (×37)); the token-cheap way to triage a build vs grepping it.
Decisive scalars (dense trace logs): … fields --path "<log>" --fields ts,Alpha,Pos.x,step:Pos,d:Yaw. Forms: Key, Key.x|.y|.z, Key.Y|.P|.R, ts, dts, d:Key, step:Key. Biggest token saver on per-frame logs.
Regression triage across runs: … diff --pathA "<before>" --pathB "<after>" — only the delta (new / gone / count-changed); omit paths to auto-pick the two newest logs.
Jump to code (if rider-mcp-enforcer is installed): … locate --path "<log>" --severityMin Error --basename gives just the distinct file:line (no bodies). Resolve each filename via Rider find_files_by_name_keyword, then read_file a small window at that line — never dump whole files.
Escape hatch: … tail --lines N for raw last N lines.

Default when the user just says "check the logs": detect → summary → search --severityMin Error, then report the errors with their locations. (… --help lists every command.)

Prefer the CLI: it has zero always-on context cost. Users who enabled the optional MCP server can use the equivalent log_* tools instead — identical output.

$ARGUMENTS

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.

5d ago First seen · 42 lines · 64 tokens per session scan A 41695ca4ae0e

Subscribe to this mod's changes

logs is a command published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 752 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.

Game development clangd claude-code code-search developer-tools

logs

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

gamedev-log-analyzer — game-engine/build log analysis

What this file has done since we first saw it

Other commands, from other repositories

sim

index

cert-check

combat-design

ui-flow-review

status