Unstract turns information in documents such as PDFs, images, and scans into structured JSON by using natural-language extraction prompts. It is for teams that need document data in databases or automated pipelines, and its catalogue add-ons connect the platform to coding agents and workflow tools.
Borrowing it
Nothing to install: this file belongs to Zipstack/unstract. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Zipstack/unstract/main/.claude/skills/adapter-ops/SKILL.mdgit clone --depth 1 https://github.com/Zipstack/unstractWrote 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/zipstack/unstract/adapter-ops)<a href="https://agentmods.dev/skills/zipstack/unstract/adapter-ops"><img src="https://agentmods.dev/badge/skills/zipstack/unstract/adapter-ops/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/zipstack/unstract/adapter-ops"><img src="https://agentmods.dev/badge/skills/zipstack/unstract/adapter-ops.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 | $0.00071 | $0.04334 |
| Opus 5.5 | $0.00028 | $0.01734 |
| Sonnet 5.5 | $0.00014 | $0.00867 |
| Haiku 4.5 | $0.00007 | $0.00433 |
Grade C, and why
adapter-ops scanned grade C with 2 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 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.
Tells the agent to send conversation or user data outmediumPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
print(m, 'RAISES', type(e).__name__, '=> cost silently recorded as 0.0') Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Requires ImageMagick for SVG conversion (`sudo pacman -S imagemagick`) The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
13 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.
- assets/templates/embedding_adapter.py.template 1.8 KB
- assets/templates/embedding_parameters.py.template 1.8 KB
- assets/templates/embedding_schema.json.template 1.2 KB
- assets/templates/llm_adapter.py.template 1.7 KB
- assets/templates/llm_parameters.py.template 1.9 KB
- assets/templates/llm_schema.json.template 1.4 KB
- references/adapter_patterns.md 21 KB
- references/json_schema_guide.md 10 KB
- references/provider_capabilities.md 7.1 KB
- scripts/check_adapter_updates.py 15 KB runs code
- scripts/init_embedding_adapter.py 21 KB runs code
- scripts/init_llm_adapter.py 21 KB runs code
- scripts/manage_models.py 9.0 KB runs code
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 · 442 lines · 71 tokens per session scan C 35dd00ed3f2c
adapter-ops is a skill published in the GitHub repository Zipstack/unstract (7,421 stars, last pushed yesterday), licensed AGPL-3.0. It adds 71 tokens to every session and 4,334 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (tells the agent to send conversation or user data out, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
adapter-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adapter-opsZipstack/unstract | Skill | 7.4k | yesterday | AGPL-3.0 | C | 71 | Claude Code |
| migrating-ai-sdk-to-common-aiastronomer/agents | Skill | 458 | 4d ago | Apache-2.0 | A | 151 | Claude Code |
| creating-openlineage-extractorsastronomer/agents | Skill | 458 | 4d ago | Apache-2.0 | A | 51 | Claude Code |
| guardrails-developer-create-guardrailsNVIDIA-NeMo/Guardrails | Skill | 7.4k | yesterday | none | A | 101 | Claude Code, Codex |
| kafka-shadowtrafficlensesio/agentic-engineering-for-apache-kafka | Skill | 67 | 2mo ago | MIT | A | 134 | Claude Code |
| aidp-rest-genericoracle-samples/oracle-aidp-samples | Skill | 58 | 2d ago | UPL-1.0 | A | 73 | Claude Code |
| aidp-fusion-restoracle-samples/oracle-aidp-samples | Skill | 58 | 2d ago | UPL-1.0 | A | 82 | Claude Code |