clear-check

clear-check is a command for coding agents from eugeniughelbur/clearmode. It costs 36 tokens per session (367 once invoked), scanned A, original, MIT.

A read-only checker that scores a file or pasted text on clarity, human tone, structure, and information density, then reports its findings.

In plain words
What is it for?
Review social posts, general copy, technical documentation, or instructions for coding agents and receive scores, findings, suggested fixes, and a top-priority problem.
Why use it?
It identifies wording and organization problems without changing the source, so you can decide what to fix yourself.

Command

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/eugeniughelbur/clearmode/clear-check
Clone the repo
git clone --depth 1 https://github.com/eugeniughelbur/clearmode

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 clear-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/eugeniughelbur/clearmode/clear-check.svg)](https://agentmods.dev/commands/eugeniughelbur/clearmode/clear-check)
Your own site
<a href="https://agentmods.dev/commands/eugeniughelbur/clearmode/clear-check"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/clearmode/clear-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 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 $0.00036 $0.00367
Opus 5 $0.00018 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00004 $0.00037

Measured 5d ago against content hash d25c913b5158, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clear-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 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.

commands/clear-check.md · 35 lines

What it actually says

/clear-check

Score text. Report. Do not edit anything.

Steps

  1. Resolve the target. A path in the argument wins. No path means the text pasted in the message, or the file currently open.
  2. Pick the profile from what the text is:
    • social for an X post, a LinkedIn post, a DM, an ad
    • general for a blog post, a newsletter, a landing page, an email
    • technical for a README, docs, an architecture note, a PR description
    • agent for a system prompt, a skill file, or instructions another agent reads
  3. Run the checker:
    python3 scripts/clearcheck.py <file> --profile <profile>
    
    For pasted text, write it to a temp file first, or pipe it with --stdin.
  4. Report in this order:
    • The score, the band, and the verdict, on one line
    • The four axis scores
    • Every error finding, with the line and the fix
    • The three highest-value warn findings, no more
    • One sentence naming the single biggest problem
  5. Stop. Do not rewrite unless the user asks.

Rules

  • Never claim a score you did not get from the checker. Run it.
  • If the checker exits 2, say what is wrong with the input instead of guessing a score.
  • Do not pad the report with the findings the checker already summarized. Point at the count.
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 · 35 lines · 36 tokens per session scan A d25c913b5158

Subscribe to this mod's changes

clear-check is a command published in the GitHub repository eugeniughelbur/clearmode (1 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 367 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.