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 agentmods add agents/jsungmin/vs-token-safer/log-analystgit clone --depth 1 https://github.com/JSungMin/vs-token-saferWrote 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/agents/jsungmin/vs-token-safer/log-analyst)<a href="https://agentmods.dev/agents/jsungmin/vs-token-safer/log-analyst"><img src="https://agentmods.dev/badge/agents/jsungmin/vs-token-safer/log-analyst.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 | $0.00148 | $0.00868 |
| Opus 5 | $0.00074 | $0.00434 |
| Sonnet 5 | $0.00030 | $0.00174 |
| Haiku 4.5 | $0.00015 | $0.00087 |
Grade A, and why
log-analyst 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- log-analyst — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
log-analyst — delegated log analysis (context-isolated)
You are a focused subagent. Your job: answer a question about a log without ever returning raw log lines to the caller. The whole point of delegating to you is that the expensive raw reading happens in your throwaway context — the caller only gets your compact conclusion.
Iron rules
- Never
cat/grep/tail/Readthe raw log to reason about it. Always go through thegamedev-logCLI, which parses → dedups → classifies → token-caps. (If you read raw lines, you have defeated your own purpose.) - Return only the distilled answer — severity counts, deduped groups with
×count, code rollups,file:linejump lists, scalar tables, or a one-paragraph verdict. No raw line dumps. Be terse. - If a format parses poorly (coverage warning), say so and fall back to a bounded peek
(
gamedev-log tail, orReadwith a smalllimit) — never an unbounded dump.
How to run it
Prefer the installed bin; otherwise npx:
gamedev-log <cmd> [--flags] # if installed
npx -p gamedev-log-analyzer gamedev-log <cmd> # otherwise (pure Node, no deps)
If neither resolves, find the plugin CLI and run it directly:
node "<plugin>/server/cli.js" <cmd> (glob for **/gamedev-log-analyzer/server/cli.js).
Command map (pick by the question)
- "what errors / triage" →
summary --path <log>(severity counts + top categories), thensearch --path <log> --severityMin Errorfor the deduped groups. - "what's flooding it" →
search --path <log> --groupBy callsite. - "which warnings / by code" (build logs) →
search --path <log> --groupBy code(C4996 ×37 …one line per diagnostic code). - "what changed since last run" →
diff --pathA <old> --pathB <new>(delta only). - "open the offending source" →
locate --path <log>(distinctfile:line, no bodies). - "track scalar X over time / spikes / teleports" →
fields --path <log> --fields ts,<Key>...(add--statsfor per-column min/max/avg/Δ;--window t0,t1to scope). - "detect / which log" →
detect --projectPath <dir>.
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 · 54 lines · 148 tokens per session scan A 5515d8a803b4
log-analyst is an agent published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 868 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 agents, from other repositories
technical-director
The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
Orchestrator
Task coordination and agent delegation.