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 NicolaiSchmid/agent-skills --skill paperless-searchgit clone --depth 1 https://github.com/NicolaiSchmid/agent-skillsWrote 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/nicolaischmid/agent-skills/paperless-search)<a href="https://agentmods.dev/skills/nicolaischmid/agent-skills/paperless-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/paperless-search/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/nicolaischmid/agent-skills/paperless-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/paperless-search.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 | $0.00032 | $0.01206 |
| Opus 5.5 | $0.00013 | $0.00482 |
| Sonnet 5.5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
paperless-search 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 2mo 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 How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paperless Document Search
Search your Paperless-ngx document archive via the REST API.
Configuration
Config file: ~/.config/paperless-search/config.json
{
"url": "https://paperless.example.com",
"token": "your-api-token-here"
}
Getting an API token
- Log into your Paperless web UI
- Click your username (top right) → "My Profile"
- Click the circular arrow button to generate/regenerate a token
Troubleshooting config
If requests fail, verify the config:
# Check config exists and is valid JSON
cat ~/.config/paperless-search/config.json | jq .
# Test connection
curl -s -H "Authorization: Token $(jq -r .token ~/.config/paperless-search/config.json)" \
"$(jq -r .url ~/.config/paperless-search/config.json)/api/documents/?page_size=1" | jq '.count'
Common issues:
401 Unauthorized: Token is invalid/expired → regenerate in web UIConnection refused: URL is wrong or server is downnullor parse error: Config file is missing or malformed
If config is broken, guide the user to provide:
- Their Paperless-ngx URL (e.g.,
https://paperless.example.com) - A valid API token from their profile page
Then create/update the config:
mkdir -p ~/.config/paperless-search
cat > ~/.config/paperless-search/config.json << 'EOF'
{
"url": "USER_PROVIDED_URL",
"token": "USER_PROVIDED_TOKEN"
}
EOF
API Examples
# Load config into variables
PAPERLESS_URL=$(jq -r .url ~/.config/paperless-search/config.json)
PAPERLESS_TOKEN=$(jq -r .token ~/.config/paperless-search/config.json)
# Full-text search
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/documents/?query=invoice+january+2025" | jq '.results[] | {id, title, created}'
# Get document with full OCR content
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/documents/123/" | jq -r '.content'
# List correspondents
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/correspondents/" | jq '.results[] | {id, name}'
# Filter by correspondent
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/documents/?correspondent__id=5" | jq
# Filter by date range
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/documents/?created__date__gte=2024-01-01&created__date__lte=2024-12-31" | jq
# List tags
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/tags/" | jq '.results[] | {id, name}'
# List document types
curl -s -H "Authorization: Token $PAPERLESS_TOKEN" \
"$PAPERLESS_URL/api/document_types/" | jq '.results[] | {id, name}'
What ships with it
1 file 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.
- 2mo ago First seen · 139 lines · 32 tokens per session scan A 6f30b04f161b
paperless-search is a skill published in the GitHub repository NicolaiSchmid/agent-skills (2 stars, last pushed 9mo ago), licensed MIT. It adds 32 tokens to every session and 1,206 once invoked, about $0.0001 per session on Opus 5.5. 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.
paperless-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paperless-searchNicolaiSchmid/agent-skills | Skill | 2 | 9mo ago | MIT | A | 32 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |