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 jaredlangleycc/nightshift-os --skill file-sweepgit clone --depth 1 https://github.com/jaredlangleycc/nightshift-osWrote 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/jaredlangleycc/nightshift-os/file-sweep)<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/file-sweep"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/file-sweep.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 5.1 | $0.00126 | $0.03848 |
| Opus 5 | $0.00063 | $0.01924 |
| Sonnet 5 | $0.00025 | $0.00770 |
| Haiku 4.5 | $0.00013 | $0.00385 |
Grade A, and why
file-sweep 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 7d 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Sweep
The weekly file management ritual. Sorts the inbox. Rotates the backups. Flags stale drafts. Closes the loose-file gap. Writes a log.
Solopreneurs without a Friday file routine spend Monday hunting for things they touched on Wednesday. File-sweep is the friction that keeps the working directory shaped for next week. Last week's shape goes to archive.
When this skill triggers
/file-sweep/friday-sweep- "Clean up files"
- "Organize my files"
- "Inbox sort"
- "Rotate backups"
- "What's stale in my drafts"
- Inside
ship-it-fridayas Step 2 - Optional: scheduled task on the user's cron, default Friday 5pm local
The folder model
The skill operates against a folder structure that customize-from-assessment set up. Default structure:
<working-directory>/
00-inbox/ ← new files land here, sorted weekly
backups/ ← hot backups, rolling 14 days
YYYY-MM-DD/
archive/ ← cold archive, kept 6 months then deletable
backups/
cold-archive-YYYY-MM-DD.tar.gz
deprecated-content/
content/ ← active content, drafts and shipped
drafts/ ← work-in-progress drafts
reports/ ← skill output logs
client-experience/ ← client-facing assets and ops
business-setup-playbook/ ← ops + course foundation
If the user's folder model differs, read CLAUDE.md > File Storage > folder_map for their canonical structure.
The six sweep tasks
Run all six in order. Each writes a section in the log.
Task 1: Inbox sort
List every file in 00-inbox/. For each file:
- Determine the target folder by file pattern (extension + name).
- Move to the target folder.
- Log the move (from → to).
Default routing rules:
*.md (draft prefix) → drafts/
*.md (final, no prefix) → content/
*.html (private slug) → langley-site/private/ (project-specific)
*.html (other) → drafts/landing-pages/
*.csv (CRM export) → business-setup-playbook/prospect-lists/YYYY-MM-DD/
*.csv (finance row export) → business-setup-playbook/
*.png|*.jpg|*.heic (asset) → brand-assets/inbox/ or content/graphics/inbox/
*.pdf (signed contract) → client-experience/signed-contracts/
*.pdf (other) → drafts/ or archive/deprecated-docs/
*.zip (backup) → backups/<today>/
*.m4a|*.wav|*.mp3 (voice) → content/voice-memos/raw/
*.mov|*.mp4 (video) → content/video/raw/
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.
- 7d ago First seen · 405 lines · 0 tokens per session scan A b6798829f558
file-sweep is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 3,848 once invoked, about $0.0006 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 skills, from other repositories
engagement-inbox-manager
Use when the user asks to "triage our comments, DMs, and mentions", "draft replies to this thread", "can we repost this fan post", or "set up inbox SLAs and an escalation path"; produces a ranked triage queue with register detection (sincere / ironic / performative / parasocial, sentiment-inversion table included …
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.