Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MECoban/screenshot-janitor/plugin install screenshot-janitorWrote 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/mecoban/screenshot-janitor/cleanup-screenshots)<a href="https://agentmods.dev/skills/mecoban/screenshot-janitor/cleanup-screenshots"><img src="https://agentmods.dev/badge/skills/mecoban/screenshot-janitor/cleanup-screenshots/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/mecoban/screenshot-janitor/cleanup-screenshots"><img src="https://agentmods.dev/badge/skills/mecoban/screenshot-janitor/cleanup-screenshots.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 | $0.00088 | $0.00851 |
| Opus 5 | $0.00044 | $0.00426 |
| Sonnet 5 | $0.00018 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade B, and why
cleanup-screenshots scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SCRIPTS="$(cat "$HOME/.claude/screenshot-janitor/scripts-path" 2>/dev/null)" How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot Janitor — Cleanup
Cleans up screenshots that piled up during this session safely: never rm;
files are moved to the Trash and can be restored. Session scope comes from the
started_at timestamp recorded by the SessionStart hook (only screenshots created
during this session).
Helper scripts live next to this plugin. Resolve their location like this (works
whether or not CLAUDE_PLUGIN_ROOT is set in skill context):
SCRIPTS="$(cat "$HOME/.claude/screenshot-janitor/scripts-path" 2>/dev/null)"
[ -z "$SCRIPTS" ] && SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
Flow
1. Find candidates
bash "$SCRIPTS/find.sh"
Interpret the output:
NO_SESSION→ no session record. Ask the user whether to scan all screenshots; if yes, runbash "$SCRIPTS/scan.sh" 0.SESSION_META:<path>→ remember this path; you will write thehandledmarker into its directory in step 5.- Following TSV lines are candidates:
<mtime_epoch>\t<size_bytes>\t<path>. - If there are no TSV lines: say "No screenshots to clean up for this session 👍" and stop.
2. Show a clear list
Present the candidates as a numbered, human-readable table. Convert bytes to MB/KB and the mtime epoch to a readable time. Example:
Found 3 screenshots from this session:
1. Screenshot 2026-06-07 at 04.44.07.png 3.6 MB 04:44
2. Screenshot 2026-06-07 at 04.44.17.png 3.4 MB 04:44
3. Screenshot 2026-06-07 at 15.49.25.png 5 KB 15:49
Total ~7.0 MB.
3. Ask for approval
Offer clear options and wait for the answer:
- All → move every candidate to the Trash.
- Some → "tell me the numbers, e.g. 1,3" → only those.
- Cancel → do nothing.
NEVER move files without approval.
4. Move to Trash
For the approved files (not permanent deletion!):
bash "$SCRIPTS/trash.sh" "/full/path/Screenshot ....png" "/another/file.png"
trash.sh is cross-platform (macOS Trash / Linux gio trash / trash-cli).
Always double-quote paths (they contain spaces). Never use rm.
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 · 89 lines · 88 tokens per session scan B 5836af3302f4
cleanup-screenshots is a skill published in the GitHub repository MECoban/screenshot-janitor (1 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 851 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
drive-screen
See and operate the user's real, physical Linux desktop through the mcp-screen MCP — screenshot any monitor and click/type/scroll/drag any visible app. Prefer screenwatch (1 fps) after graphs/maps/canvases/loaders so thrashing UIs are caught like a human watches, not one freeze-frame. Use whenever the user points at…
docs-drift
Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.