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 Dhirenderchoudhary/unmarkk --skill unmark-filesgit clone --depth 1 https://github.com/Dhirenderchoudhary/unmarkkWrote 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/dhirenderchoudhary/unmarkk/unmark-files)<a href="https://agentmods.dev/skills/dhirenderchoudhary/unmarkk/unmark-files"><img src="https://agentmods.dev/badge/skills/dhirenderchoudhary/unmarkk/unmark-files/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/dhirenderchoudhary/unmarkk/unmark-files"><img src="https://agentmods.dev/badge/skills/dhirenderchoudhary/unmarkk/unmark-files.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00113 | $0.01513 |
| Opus 5 | $0.00056 | $0.00757 |
| Sonnet 5 | $0.00023 | $0.00303 |
| Haiku 4.5 | $0.00011 | $0.00151 |
Grade A, and why
unmark-files scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8765/health How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Removing metadata from files
Files carry more than their contents. A phone photo knows where it was taken to within a few metres and which camera took it. A Word document knows who wrote it, for which company, and how many minutes they spent. A PDF exported from a design tool knows the local path of the file it came from.
None of that is visible. All of it travels when the file is sent.
This skill drives unmark, which removes it. Everything runs on the user's
machine; no file is uploaded anywhere.
Before anything else: inspect
Never clean before showing the user what is there. The report is usually the thing they actually wanted — people are more often surprised by what a file contains than they are interested in the removal step.
unmark inspect path/to/file
Add --json when you need to reason about the result rather than show it.
Report back in the user's terms. "This photo contains the GPS coordinates where it was taken, your camera's serial number, and the timestamp" is useful. "has_c2pa: false, privacy.hasLocation: true" is not.
Then clean
unmark clean path/to/file # writes path/to/file.cleaned.ext
unmark clean path/to/file -o output.ext # explicit destination
unmark clean path/to/file --in-place # overwrite, keeping a .bak
Default to writing a new file. In-place editing of someone's original is a decision they should make deliberately, not one you make for them.
After cleaning, say what was actually removed — the actions list is specific,
so use it. If residual reports anything left, or degraded is true, say that
too rather than reporting a clean success.
Auditing more than one file
unmark scan ~/Pictures --quiet # only the files that need attention
unmark scan ./site --stylometry --json # everything, machine-readable
unmark audit-site https://example.com/sitemap.xml --quiet
scan walks a directory. audit-site fetches the URLs in a sitemap — it is
the one command that touches the network, and it only ever issues GETs against
URLs the user named.
What ships with it
3 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.
- 11d ago First seen · 155 lines · 113 tokens per session scan A 64ad3bb607e1
unmark-files is a skill published in the GitHub repository Dhirenderchoudhary/unmarkk (6 stars, last pushed 12d ago), licensed MIT. It adds 113 tokens to every session and 1,513 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
write-architecture-docs
Write or rewrite architecture subsystem docs, ADRs, and reference material for the engineering team. Use when creating, updating, or reviewing docs under docs/architecture docs/, or when the user asks you to write documentation that describes the system's design.
pr-checklist
Use when opening or finalizing a GitHub PR for OpenMetadata. Walks through the repo PR template — linked issue, high-level design (for big PRs), unit/integration/Playwright tests + coverage, UI screen recording, and manual test steps — then drafts a fully-filled PR body and (optionally) creates the PR.
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.