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 skills add VonTerraProject501c3/slushpile --skill removing-ai-tellsgit clone --depth 1 https://github.com/VonTerraProject501c3/slushpileWrote 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/skills/vonterraproject501c3/slushpile/removing-ai-tells)<a href="https://agentmods.dev/skills/vonterraproject501c3/slushpile/removing-ai-tells"><img src="https://agentmods.dev/badge/skills/vonterraproject501c3/slushpile/removing-ai-tells/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.
<a href="https://agentmods.dev/skills/vonterraproject501c3/slushpile/removing-ai-tells"><img src="https://agentmods.dev/badge/skills/vonterraproject501c3/slushpile/removing-ai-tells.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 202 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00063 | $0.02302 |
| Opus 5 | $0.00032 | $0.01151 |
| Sonnet 5 | $0.00013 | $0.00460 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
removing-ai-tells 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Removing AI Tells
Iterative passes over a draft, removing the patterns that make a fatigued reader think "a machine wrote this" before they consciously work out why.
Announce at start: "Removing AI tells from $FILE. Working on a copy, three passes maximum."
Arguments:
$1— path to the file to clean
Example:
/slushpile:removing-ai-tells applications/Acme/Engineering/Staff-SRE/cover_letter.txt
Why This Is Separate From the Voice Agent
The voice agent writes in a person's voice. That is a different job from hunting a specific list of patterns, and combining them produces worse results at both.
A voice agent asked to "write well and also avoid these forty patterns" will trade one against the other silently. Running the passes separately means each one has a single objective, and the gatekeeper between them can see exactly what changed and why.
The gatekeeper is the point. About a third of what a tell-hunting pass flags is doing real work in the document. Applied without review, this process reliably makes prose worse — flatter, more uniform, and stripped of exactly the moves that made it sound like a person. That is the failure mode this skill is built around, not an edge case.
Prerequisites
- The file to clean
- The voice agent named in
preferences.yamlundervoice.agent(default:aaddrick-voice) - The user's voice agent definition. A habit documented there outranks this entire checklist.
The Process
1. Work on a copy
Never edit the original.
cp cover_letter.txt cover_letter.v2.txt
Keeping the previous version is what lets you revert a rejected change precisely rather than re-editing from memory.
2. First pass
Send the copy to a fresh instance of the voice agent with the checklist below. Ask it to edit the file directly and return a summary of every change with its rationale.
The rationale is not optional. A change you cannot evaluate is a change you have to accept or revert blind.
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.
- 12d ago First seen · 205 lines · 63 tokens per session scan A 97880b860806
removing-ai-tells is a skill published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 26d ago), licensed MIT. It adds 63 tokens to every session and 2,302 once invoked, about $0.0003 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.
Other skills, from other repositories
create-diagram
Create architecture diagrams from a local codebase or system description. Use when the user asks to diagram a repo, map system architecture, show component relationships, create drill-down views, or explain a system visually with tld.
resume
Generate a tailored resume AND cover letter for a job description via the native four-role Resume Team, score both against ATS and HR rubrics, create DOCX files, and update the tracker. Use when the user pastes a job description and wants a complete application package (resume plus cover letter) with dual scoring and…
writing-coach
Human-voice writing coach that rewrites resumes and cover letters for brevity, burstiness, plain language, and authentic impact, and blocks AI-sounding prose. Use when the user wants to improve writing quality, fix robotic or generic AI-sounding text, cut fluff, strengthen bullets and summaries, or pass the…
find-jobs
Search live job boards for roles that match the master resume, then score and rank them by ATS and HR fit. Use when the user wants to discover or find jobs, search openings by title or location, wants remote roles, or asks which live listings best match their background. Uses the discoverjobs MCP tool and never…
cover-letter
Create a compelling one-page, human-voice cover letter for a job description and generate the final DOCX. Use when the user wants a cover letter only (no resume), pastes a JD and asks for a letter, or needs a letter to accompany an already-tailored resume. Runs the mandatory humanvoiceaudit before producing the DOCX.
job-fit
Run the deterministic, digest-bound candidate-fit gate that scores the configured master resume against an exact job description before any resume tailoring. Use when the user wants a GO/NO-GO fit check on a JD, asks "should I apply", or before starting resume work, to confirm score >= 70 with zero hard knockouts.…