Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add JSungMin/rider-mcp-enforcer/plugin install gamedev-log-analyzerWrote 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/commands/jsungmin/rider-mcp-enforcer/enforce)<a href="https://agentmods.dev/commands/jsungmin/rider-mcp-enforcer/enforce"><img src="https://agentmods.dev/badge/commands/jsungmin/rider-mcp-enforcer/enforce/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/commands/jsungmin/rider-mcp-enforcer/enforce"><img src="https://agentmods.dev/badge/commands/jsungmin/rider-mcp-enforcer/enforce.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 | $0.00042 | $0.00587 |
| Opus 5 | $0.00021 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
enforce scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to enforce — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
gamedev-log-analyzer — enforcement control
A PreToolUse hook intercepts two raw-log vectors and steers them to gamedev-log (parse + dedup +
token-cap) instead of dumping raw lines into context:
- Bash raw reads (
grep/rg/ack/ag/findstr/tail/head/cat) over a.log/.jsonl/ rotated.log.Nfile or aLogs/·Saved/Logs/path. - Read tool — an unbounded read of a large (≥ 200 KB) log file. A sliced read (
offset/limit) always passes (one-step escape + fallback for poorly-parsed formats); small logs pass.
Code grep (.cpp/.cs/src/…), non-log reads, and the Grep tool (already result-capped) pass through.
Run the CLI through Bash (no setup; pure Node):
node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" enforce # show current mode + source
node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" enforce warn # allow, but nudge (soft)
node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" enforce off # disable enforcement
node "${CLAUDE_PLUGIN_ROOT}/server/cli.js" enforce block # re-enable (default)
Modes:
- warn (default) — allow the command, but inject the
gamedev-logequivalent into the model's context as a nudge. Steers without friction. - block — deny the raw read (exit 2) and show the nudge — the command does not run. Opt-in.
- off — silent passthrough, no enforcement.
Mode precedence: env GDLOG_ENFORCE > ~/.gamedev-log-analyzer/config.json ("enforce") > default
block. For a one-shot bypass in the current shell, prefix the command with GDLOG_ENFORCE=off. After
changing the persisted mode, run /reload-plugins.
When a user hits the block but genuinely needs the raw bytes: for a Read, re-Read with offset/limit
(a bounded slice always passes); for Bash tail -f live-watching, suggest enforce warn (or off)
rather than working around the hook.
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.
- 9d ago First seen · 39 lines · 42 tokens per session scan A 256938c38860
enforce is a command published in the GitHub repository JSungMin/rider-mcp-enforcer (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 587 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to enforce, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
plan
Project spec (no args) or feature FRD (with args).
debug
Structured debugging with parallel investigation agents.
init
Analyze codebase and generate CLAUDE.md with project conventions.
release
Generate changelog, bump version, and create git tag.
review
Multi-agent code review with parallel validation.
cancel-ship
Cancel active ship pipeline.