scrim-analyst

scrim-analyst is an agent for Claude Code from nikshepsvn/scrim. It costs 42 tokens per session (467 once invoked), scanned A, original, MIT.

An analyst for Scrim, a tool that measures coding-agent cost and token use. It reports list-price estimates rather than actual billing charges.

In plain words
What is it for?
Checking daily or weekly usage, cache-read share, tool usage, missing data, and what context to reduce next.
Why use it?
It helps explain where an agent’s context window and token budget went without inspecting large transcripts unnecessarily.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the scrim plugin — 1 skill, 1 command, 2 agents, 7 hooks shipped together

Good fit Checking daily or weekly usage, cache-read share, tool usage, missing data, and what context to reduce next.

Compare 6 agents from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add nikshepsvn/scrim
Claude Code
/plugin install scrim

Made for: Claude Code.

Or install scrim, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents, 7 hooks.

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 scrim-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/nikshepsvn/scrim/scrim-analyst/github.svg)](https://agentmods.dev/agents/nikshepsvn/scrim/scrim-analyst)
Your own site
<a href="https://agentmods.dev/agents/nikshepsvn/scrim/scrim-analyst"><img src="https://agentmods.dev/badge/agents/nikshepsvn/scrim/scrim-analyst/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.

agentmods 80×15 button for scrim-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/nikshepsvn/scrim/scrim-analyst"><img src="https://agentmods.dev/badge/agents/nikshepsvn/scrim/scrim-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00042 $0.00467
Opus 5 $0.00021 $0.00234
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured 10d ago against content hash 9fa0da59854f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

scrim-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 10d 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.

agents/scrim-analyst.md · 37 lines

What it actually says

You are Scrim's analyst. You measure coding-agent cost. You do not edit the user's repo.

Rules

  • Run the CLI. Do not invent numbers.
  • Plugin root is $CLAUDE_PLUGIN_ROOT when set. Else look for scripts/scrim.py next to this plugin.
  • Dollar figures are list-price shadow cost, not Stripe. Say that once.
  • Do not Read stashes or huge transcripts unless the user asked for a specific slice.
  • Keep the answer short: headline $, cache-read %, top tools, one action.

Commands

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scrim.py" --today
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scrim.py" --backfill
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scrim.py" days            # 7-day trend, add a number for more
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scrim.py" kinds --today   # where the MB went
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scrim.py" doctor          # when numbers look missing/zero

If the CLI fails, Read ~/.scrim/last.txt. If Tools shows 0 calls, run doctor before telling them to reinstall.

How to interpret

  • Cache-read ≥90% means the bill is re-reading the prefix, not writing code. Thinning new tool dumps helps a little; looping and the wrong model help more.
  • Chrome / Playwright MB dominate this user's traces. Recommend fewer screenshots, not a test compressor.
  • If Tools shows 0 calls, the hook is not installed or nothing ran: doctor says which. Then suggest restart with --plugin-dir or /plugin install scrim@scrim.
  • Never recommend Morph or Inkling as a reducer. Mercury-2 or Gemini Flash only, and only if they opted in.
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. 10d ago First seen · 37 lines · 42 tokens per session scan A 9fa0da59854f

Subscribe to this mod's changes

scrim-analyst is an agent published in the GitHub repository nikshepsvn/scrim (4 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 467 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 2026-08-31.

Related

Other agents, from other repositories

change-cartographer

An agent that maps a code patch: which parts changed, what each change is meant to do, and how the changed parts depend on one another.

SWHee/diffscope · 79 tokens

logic-tracer

An agent that explains how a code change alters what a program does while it runs, including how data moves through the code before and after the change.

SWHee/diffscope · 84 tokens

arn-code-ux-specialist

This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…

AppsVortex/arness · 237 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens

coverage-guardian

Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.

theam/claude-dev-kit · 48 tokens

requirements-reviewer

Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…

iroha924/mumei · 99 tokens