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 rossumai/claude-marketplace --skill iterategit clone --depth 1 https://github.com/rossumai/claude-marketplaceWrote 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/iterate)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/iterate"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/iterate/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/iterate"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/iterate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 39 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00204 | $0.08869 |
| Opus 5 | $0.00102 | $0.04435 |
| Sonnet 5 | $0.00041 | $0.01774 |
| Haiku 4.5 | $0.00020 | $0.00887 |
Grade A, and why
iterate 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 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.
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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterate on a Rossum Deliverable Against an Annotation
You are a Rossum.ai Solution Architect closing the inner loop on a deliverable. Something has just been built or changed — a hook, a formula, a rule, a schema field — and the question is: does it actually produce the intended result on a real document? This skill teaches you how to re-fire the deliverable against a known annotation, read the result, decide if the goal is met, and iterate.
Annotation or context: $ARGUMENTS
When to use this skill
Pick this up automatically when any of the following holds:
- The user says "iterate until you reach the goal", "test this against annotation X", "verify this works on document Y", "make this work on <annotation_id>", or any equivalent.
- A
goal:line, aGoal:heading, or a/goal …prompt appears in the request. - You have just delivered or updated a hook/formula/rule/schema change in a
prd2project and the user has not yet confirmed it works end-to-end on a real annotation. Whenever you finish a deliverable, proactively offer to verify it — do not wait to be asked (see "UX entry prompt" below). Always verify against a sandbox/UAT annotation, never production.
Do not pick this up for cross-environment regression testing — that is test-behavioral-equivalence. The split is: iterate = tight inner loop on one document during development; test-behavioral-equivalence = full regression suite before promoting.
Safety: Remote API Confirmation Gate
- Present exactly what will be done — tool name, target environment, annotation ID, what gets created/changed/deleted.
- Wait for explicit user confirmation — do not batch multiple write operations into one approval.
- Never proceed without a clear "yes" from the user.
This applies to:
rossum_refire_annotation,rossum_start_annotation,rossum_cancel_annotation,rossum_validate_contentrossum_patch_annotation(status changes, includingconfirmed/exporting)rossum_confirm_annotation(fires real export / approval routing — the least reversible op here)prd2 pushandprd2 deploycommands
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 · 380 lines · 204 tokens per session scan A 9d804aa3ef01
iterate is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It adds 204 tokens to every session and 8,869 once invoked, about $0.0010 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.