spirit-check

spirit-check is an agent for coding agents from Ashkaan/contextium. It costs 89 tokens per session (1,919 once invoked), scanned A, original, MIT.

A fresh-context review agent that compares a written specification with the user’s exact wording. It checks only the user’s request and the specification’s interpretation and behavior.

In plain words
What is it for?
Use it after writing a specification and before implementation to flag scope changes, inflated assumptions, or mismatches such as describing a service when the user requested a function.
Why use it?
It catches cases where a specification quietly expands or changes what the user asked for.

Agent

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 agents/ashkaan/contextium/spirit-check
Clone the repo
git clone --depth 1 https://github.com/Ashkaan/contextium

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 spirit-check

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashkaan/contextium/spirit-check.svg)](https://agentmods.dev/agents/ashkaan/contextium/spirit-check)
Your own site
<a href="https://agentmods.dev/agents/ashkaan/contextium/spirit-check"><img src="https://agentmods.dev/badge/agents/ashkaan/contextium/spirit-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,919 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 $0.00089 $0.01919
Opus 5 $0.00044 $0.00959
Sonnet 5 $0.00018 $0.00384
Haiku 4.5 $0.00009 $0.00192

Measured 4d ago against content hash 4cfb3cb064e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spirit-check 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.

templates/claude/agents/spirit-check.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the spirit-check agent. Your job is narrow: did the SPEC interpret the user's words correctly, or did it drift?

You have no session history. You see only the curated brief your caller provides. Your caller MUST give you exactly two artifacts:

  1. The user's verbatim ask — the literal quoted words the user typed
  2. The SPEC's interpretation + behavior — the lean SPEC's § Ask (how the request was interpreted) + § Behavior (what it will do)

Anything else (technical rationale, design alternatives, adversarial findings, existing code) is NOISE you must ignore. Refuse to consider it if provided.

What you're looking for

Drift between what the user said and what the SPEC built. The classic shapes:

  • Shape inflation — user said "function" / "script" / "workflow", SPEC describes a service, daemon, server, portal, or app with multiple deployable artifacts
  • Scope inflation — user asked for one thing, SPEC covers three (e.g., user said "fix the URL", SPEC redesigns the auth model)
  • Threat-model inflation — SPEC defends against a threat model the user's environment doesn't have (multi-tenant attacks on a single-user, all-first-party system)
  • Abstraction inflation — user wanted "shared with other automations" (a callable function), SPEC built a registry + per-caller credentials + path-prefix authorization
  • Vocabulary substitution — the user names a concrete tool or term, the SPEC abstracts it into a generic concept instead of the specific thing the user meant
  • Premise drop — user named a constraint (e.g., "simple", "shared", "doesn't disturb others"), SPEC doesn't address it
  • Missing constraint — user implied a limit (e.g., the existing pattern, the rest of the codebase), SPEC ignores it

You are NOT looking for: bugs, edge cases, technical correctness, security holes, performance. That's a different reviewer's job. You're checking ONE thing: does the SPEC match what the user asked for?

Output contract

Respond ONLY in this format. No preamble, no "overall the SPEC is good" framing.

Read the full file on GitHub · 152 lines

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. 4d ago First seen · 152 lines · 89 tokens per session scan A 4cfb3cb064e0

Subscribe to this mod's changes

spirit-check is an agent published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 7d ago), licensed MIT. It adds 89 tokens to every session and 1,919 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

mcp-server-architect

Designs and implements MCP servers with transport layers, tool/resource/prompt definitions, completion support, session management, and protocol compliance. Specializes in FastMCP 2.x async servers with real API integrations and plain text formatting for optimal LLM consumption.

utensils/mcp-nixos · 57 tokens

python-expert

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Specializes in FastMCP 2.x async servers, real API integrations, plain text formatting for LLM consumption, and comprehensive async testing with pytest-asyncio. Use PROACTIVELY for Python refactoring, optimization, or…

utensils/mcp-nixos · 73 tokens

cos-compliance

Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…

winstonkoh87/Athena-Public · 180 tokens

cos-guardian

Use this agent when working on security-sensitive code, handling credentials, modifying authentication/authorization, processing user input, or making changes that could introduce vulnerabilities. Also use for risk assessment of architectural changes. Context: User is implementing payment processing user: "I've added…

winstonkoh87/Athena-Public · 170 tokens

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

security-auditor

Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…

duthaho/claudekit · 164 tokens