discover

discover is a command for coding agents from JSungMin/vs-token-safer. It costs 41 tokens per session (349 once invoked), scanned A, original, MIT.

A local command that measures how often Claude Code transcripts read logs directly instead of using gamedev-log. It reports aggregate counts, estimated token use, and a coverage ratio without showing log contents.

In plain words
What is it for?
Use it to audit the current project's sessions, recent sessions, all projects in aggregate, or one transcript for missed log-analysis savings.
Why use it?
It reveals where raw log reading may be wasting context and tokens while keeping transcript details private.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the gamedev-log-analyzer plugin — 1 skill, 3 commands, 1 agent, 1 hook shipped together

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/discover
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.

agentmods badge for discover

README.md
[![agentmods](https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/discover.svg)](https://agentmods.dev/commands/jsungmin/vs-token-safer/discover)
Your own site
<a href="https://agentmods.dev/commands/jsungmin/vs-token-safer/discover"><img src="https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/discover.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00349
Opus 5 $0.00020 $0.00175
Sonnet 5 $0.00008 $0.00070
Haiku 4.5 $0.00004 $0.00035

Measured 5d ago against content hash fa9153866f21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

discover 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.

gamedev-log-analyzer/commands/discover.md · 29 lines

What it actually says

gamedev-log — discover (missed token savings)

Quantifies how often logs were read raw (grep/tail/cat over a .log, or a full-file Read) instead of through gamedev-log, so you can see where tokens leaked. Adapted from RTK's discover, scoped to logs.

Run from the project root you launched Claude Code from (it keys off the working directory):

gamedev-log discover                 # this project, all sessions
gamedev-log discover --since 7       # sessions from the last 7 days
gamedev-log discover --all           # every project — cross-project AGGREGATE only
gamedev-log discover --session <path-to.jsonl>

(or node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" discover …)

It reports aggregate counts + coarse, estimated token numbers + a coverage ratio (reads routed through gamedev-log vs bypassed). It is local-only — reads transcripts, writes/transmits nothing, and never prints a command, file path, or any log content (proprietary). Token counts are estimated (chars / 4), rounded coarsely, and labelled as estimates. Some "bypassed" reads are legitimate (a bounded peek, or a format gamedev-log parses poorly). The same detectors that drive the enforcement hook drive this, so the two never disagree.

$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.

  1. 5d ago First seen · 29 lines · 41 tokens per session scan A fa9153866f21

Subscribe to this mod's changes

discover is a command published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 349 once invoked, about $0.0002 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.