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 rossumai/claude-marketplace/plugin install rossum-saWrote 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/rossumai/claude-marketplace/parts-index)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/parts-index"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/parts-index/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/rossumai/claude-marketplace/parts-index"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/parts-index.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 | $0.00082 | $0.01717 |
| Opus 5.5 | $0.00033 | $0.00687 |
| Sonnet 5.5 | $0.00016 | $0.00343 |
| Haiku 4.5 | $0.00008 | $0.00172 |
Grade A, and why
parts-index 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parts Index
The parts library lives at ${CLAUDE_PLUGIN_ROOT}/parts/<axis>/<name>/ — each
part is a part.json contract + a fragment.* config body (with «param» seams)
- a
README.md. Parts are drop-ins built on top of the reference packs. Onlystandard-maturity parts are safe to compose automatically.
Always read fragments through ${CLAUDE_PLUGIN_ROOT}, never a repo-relative path. You
are normally cd'd into a customer's prd2 project, not this marketplace repo, so
plugins/rossum-sa/parts/… resolves to nothing there: you would see the index below,
fail to read any fragment, and improvise from a one-line summary. ${CLAUDE_PLUGIN_ROOT}
points at the installed plugin wherever it lives.
To use a part: read its part.json for params/produces/consumes, copy the
fragment, fill the «param» seams, and confirm its consumes fields exist in the
schema. See ${CLAUDE_PLUGIN_ROOT}/parts/README.md for the full contract — including
what produces/consumes mean (post-fill schema field ids) and the type a param declares.
Capture (parts/capture/)
| part | summary | produces |
|---|---|---|
capture-page-text-to-field |
park first/last page OCR text into schema fields on initialize, so a reasoning field or LLM prompt has document content to read |
first_page_field, last_page_field |
Matching (parts/matching/)
| part | summary | produces |
|---|---|---|
mdh-exact-to-fuzzy-cascade |
exact-ID → fuzzy-name, score-gated | matched_id, matched_name |
mdh-compound-must-should-search |
boosted must + optional should + filter Atlas Search | matched_id |
mdh-fuzzy-score-normalization |
fuzzy name search with length-ratio normalization | matched_id, match_score |
mdh-picker-with-exact-preselect |
auto-select exact; else placeholder + pick-list | selected_key, selected_label |
mdh-lookup-join-then-match |
match parent, $lookup to sub-collection, match child | matched_child_id |
Export (parts/export/)
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.
- 1mo ago Changed · +2 lines e5366e610185
- 1mo ago Changed · +10 lines d487ba67de9b
- 1mo ago Changed · +22 lines · +11 tokens per session 9d3986832629
- 2mo ago First seen · 67 lines · 71 tokens per session scan A 6b36919f47a4
parts-index is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 1,717 once invoked, about $0.0003 per session on Opus 5.5. 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.
parts-index compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| parts-indexrossumai/claude-marketplace | Skill | 5 | 5d ago | MIT | A | 82 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 5d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 579 | yesterday | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 257 | 2d ago | MIT | A | 106 | Claude Code |
| telnyx-messaging-hosted-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 45 | Claude Code |