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 commands/eugeniughelbur/clearmode/clear-checkgit clone --depth 1 https://github.com/eugeniughelbur/clearmodeWrote 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/eugeniughelbur/clearmode/clear-check)<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>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 | $0.00036 | $0.00367 |
| Opus 5 | $0.00018 | $0.00183 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
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.
What it actually says
/clear-check
Score text. Report. Do not edit anything.
Steps
- Resolve the target. A path in the argument wins. No path means the text pasted in the message, or the file currently open.
- Pick the profile from what the text is:
socialfor an X post, a LinkedIn post, a DM, an adgeneralfor a blog post, a newsletter, a landing page, an emailtechnicalfor a README, docs, an architecture note, a PR descriptionagentfor a system prompt, a skill file, or instructions another agent reads
- Run the checker:
For pasted text, write it to a temp file first, or pipe it withpython3 scripts/clearcheck.py <file> --profile <profile>--stdin. - Report in this order:
- The score, the band, and the verdict, on one line
- The four axis scores
- Every
errorfinding, with the line and the fix - The three highest-value
warnfindings, no more - One sentence naming the single biggest problem
- 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.
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.
- 5d ago First seen · 35 lines · 36 tokens per session scan A d25c913b5158
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.
Other commands, from other repositories
deslop
Audit and rewrite text so it stops reading as AI-generated.
write-post
Draft a LinkedIn text post in the user's voice with inline humanizer drafting constraints.
audit-profile
Diagnose the user's LinkedIn profile section by section with severity-rated fixes.
build-carousel
Produce a LinkedIn carousel SPEC (slide copy + visual brief + image-gen prompts) for assembly in Canva or Figma.
find-ideas
Interview the user to surface specific, postable LinkedIn ideas from their actual work.
repurpose-content
Turn one piece of source content into 3-7 distinct LinkedIn pieces from different angles.