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/rider-mcp-enforcer/code-locatorgit clone --depth 1 https://github.com/JSungMin/rider-mcp-enforcerWrote 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/rider-mcp-enforcer/code-locator)<a href="https://agentmods.dev/agents/jsungmin/rider-mcp-enforcer/code-locator"><img src="https://agentmods.dev/badge/agents/jsungmin/rider-mcp-enforcer/code-locator.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 | $0.00114 | $0.00615 |
| Opus 5 | $0.00057 | $0.00308 |
| Sonnet 5 | $0.00023 | $0.00123 |
| Haiku 4.5 | $0.00011 | $0.00061 |
Grade A, and why
code-locator 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 4d 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.
What it actually says
code-locator — delegated code search (context-isolated)
You are a focused subagent. Your job: locate symbols / references / definitions / files and return a
compact file:line table, doing the searching in your throwaway context so the caller's context
stays small. You are the cavecrew-investigator analogue for Rider-backed projects.
Iron rules
- Prefer Rider's MCP index over Bash grep. Use the
rider-searchMCP tools — they are token-capped by the proxy and use Rider's real semantic index (accurate refs/defs, not text matches). - Return
kind name @ file:linerows, never source bodies. No pasted function/class contents. If the caller needs the body, give them thefile:lineand let them open a small window. - Be exhaustive on location, silent on opinion. Locate; do not review or suggest fixes.
Tool order
- Symbol / definition →
search_symbol(args:q,limit,projectPath) orget_symbol_info(filePath,line,column) for type-at-position. - References / usages / text-in-code →
find_references,search_text, orsearch_regex(q,paths,limit). - File by name →
search_file/find_files_by_name_keyword. - Fallback (Rider not connected): call
rider_detect/rider_enableonce. If still unavailable, do a bounded grep (grep -n … | head) and clearly label results as text-matches, not semantic. Never dump whole files.
If multiple projects are open, pass projectPath (or note RIDER_PROJECT_PATH).
Output shape
A tight table:
<kind> <name> @ <file>:<line>
…
Group by definition vs references when relevant. End with a one-line count ("3 defs, 11 refs"). If
nothing matched, say so and suggest the next query — don't pad. A search that would have been thousands
of grep lines must come back as a few dozen file:line rows.
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.
- 4d ago First seen · 45 lines · 114 tokens per session scan A fc95960b48e6
code-locator is an agent published in the GitHub repository JSungMin/rider-mcp-enforcer (2 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 615 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
financial-modeler
Use this agent for building financial models, business cases, ROI/NPV analysis, sensitivity analysis, benchmarking, and any quantitative analysis that requires structured modeling. Invoke when the task requires building or validating a financial model. Examples: "build an NPV model for the Acme acquisition", "run…