Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/anshaneja5/markscrubnpx agentmods add skills/anshaneja5/markscrub/remove-ai-marksWrote 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/anshaneja5/markscrub/remove-ai-marks)<a href="https://agentmods.dev/skills/anshaneja5/markscrub/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/anshaneja5/markscrub/remove-ai-marks/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/anshaneja5/markscrub/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/anshaneja5/markscrub/remove-ai-marks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Excessive Agency · line 62 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium System Prompt Leakage · line 58 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00091 | $0.00689 |
| Opus 5 | $0.00046 | $0.00345 |
| Sonnet 5 | $0.00018 | $0.00138 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
remove-ai-marks 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remove AI marks (markscrub)
Privacy / provenance hygiene for content the user owns.
Do not claim results are “human-written,” “undetectable,” or that they pass a vendor detector. Separate verifiable cleans from best-effort rewrites in every summary.
Setup
Prefer the project-local CLI:
# from the markscrub repo
npm install
npx tsx src/cli.ts help
# or after build:
npm run build && node dist/cli.js help
If markscrub is on PATH, use that instead.
Workflow
1. Inspect first
markscrub inspect path/to/file --json
Summarize Unicode hits and metadata/C2PA hints briefly.
2. Deterministic clean (Layer A + files)
markscrub clean INPUT -o OUTPUT --json
Always do this for matching inputs. Re-inspect OUTPUT when useful.
PDF cleaning needs exiftool on PATH; otherwise report that PDF was left unchanged.
3. Offer rewrite (Layer B) for prose
After clean, always offer a statistical-mark reduction pass for natural-language text. Do not skip silently.
# Default: print a strong paraphrase prompt (no API key required)
markscrub rewrite INPUT --backend print-prompt
# Local presets
markscrub rewrite INPUT -o OUT.md --backend ollama --model llama3.2
markscrub rewrite INPUT -o OUT.md --backend lmstudio
# OpenAI-compatible cloud
export MARKSCRUB_REWRITE_API_KEY=...
markscrub rewrite INPUT -o OUT.md --backend openai --strength paraphrase
Model hygiene: Prefer a rewrite model different from the suspected origin model.
Also useful:
markscrub inspect DIR --recursive --fail-on-findings --sarif out.sarif
markscrub clean DIR -o OUTDIR --recursive --diff
printf 'text' | markscrub clean - -o cleaned.txt
./scripts/install-skill.sh cursor
Then run Layer A again on the rewrite result (markscrub clean).
4. Report residual risk honestly
Use the JSON report fields:
findings[].verifiable— true for Unicode/metadata actionsresidualRisk— always mention sampling marks may remain
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 98 lines · 91 tokens per session scan A ffdeb85dc8f1
remove-ai-marks is a skill published in the GitHub repository anshaneja5/markscrub (66 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 689 once invoked, about $0.0005 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.