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 agentmods add skills/managedcode/dotnet-skills/managedcode-markitdownnpx skills add managedcode/dotnet-skills --skill managedcode-markitdowngit clone --depth 1 https://github.com/managedcode/dotnet-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/managedcode/dotnet-skills/managedcode-markitdown)<a href="https://agentmods.dev/skills/managedcode/dotnet-skills/managedcode-markitdown"><img src="https://agentmods.dev/badge/skills/managedcode/dotnet-skills/managedcode-markitdown.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 | $0.00113 | $0.00430 |
| Opus 5 | $0.00056 | $0.00215 |
| Sonnet 5 | $0.00023 | $0.00086 |
| Haiku 4.5 | $0.00011 | $0.00043 |
Grade A, and why
managedcode-markitdown 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 yesterday.
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- dotnet-managedcode-markitdown — 91% identical, 6 lines differ
- dotnet-managedcode-markitdown — 91% identical, 4 lines differ
What it actually says
ManagedCode.MarkItDown
Trigger On
- integrating
ManagedCode.MarkItDowninto document ingestion flows - converting office or rich-text content into Markdown for downstream processing
- reviewing indexing, chunking, or AI-preparation pipelines that depend on Markdown output
- documenting file-conversion steps for a .NET application
Workflow
- Identify the document sources the app actually handles.
- Decide where Markdown conversion belongs in the pipeline:
- before indexing
- before chunking
- before AI summarization or enrichment
- Keep conversion isolated behind one ingestion or processing service instead of scattering format handling everywhere.
- Validate real converted output for structure, links, headings, and attachment handling.
- Document which downstream stage depends on the produced Markdown.
flowchart LR
A["Input document"] --> B["ManagedCode.MarkItDown conversion"]
B --> C["Markdown output"]
C --> D["Indexing, chunking, or AI workflow"]
Deliver
- guidance on where ManagedCode.MarkItDown fits in a real processing pipeline
- conversion-boundary recommendations for application design
- output-validation expectations for document ingestion
Validate
- the converted Markdown is good enough for the actual downstream consumer
- conversion is isolated in one clear pipeline step
- tests or review samples cover the real input formats the application claims to support
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.
- yesterday First seen · 45 lines · 113 tokens per session scan A 93bd3f2a6b0d
managedcode-markitdown is a skill published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 430 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 2026-09-03.
Other skills, from other repositories
carta-consolidating-pnl
Consolidating P&L (Income Statement) across the entities of a firm, for any period the user picks — a month, quarter, year, or start-to-end date range. Produces TWO Excel tabs: detail P&L (Period + YTD Actual/Budget/Variance/%) and executive Summary P&L formula-linked to detail. Optional tag-view breaks Actuals down…
carta-compensation-benchmarks
Retrieves Carta Total Compensation market benchmarks (salary, equity, total cash) for a role. Output to chat or CSV. Market benchmarks are triggered by queries like: "sales benchmarks", "comp benchmarks", "market rate", "what does a [role] pay", "put benchmarks in a CSV", "get benchmarks", "get carta's market…
carta-consolidating-balance-sheet
Generate a consolidating Balance Sheet for all entities under a firm for a given month and write it as a side-by-side Excel tab with Assets / Liabilities / Equity sections and a Total column. Sourced from Carta MCP (firm/entity resolution + DWH SQL). TRIGGER when the user asks for "balance sheet of all entities of…
carta-reporting-markdown
Internal subskill for carta-reporting. Drives the full Claude Code interaction: schema preview, customization checkpoint, transform config (filtering, sorting, formulas, aggregations), output preview, and hand-off to carta-reporting-excel. Invoked by carta-reporting (Claude Code path) after the preview file lands. Not…
carta-brand-extraction
Generates a brand board from a firm's website URL and optional user-provided assets. Analyzes the website to extract theme colors, typography, logos, and imagery, then produces a polished brand board as an HTML artifact, PDF, slide deck, or React component. Trigger phrases: "build a brand board", "create a brand…
carta-cap-table:issuance-import
Internal file-ingest sub-skill for carta-issuance. Turns an uploaded spreadsheet (.xlsx/.xlsm/.csv/.tsv) or document (.pdf/.docx) into the knowns.rows the config panel already consumes, for both certificates and option grants. Not invocable directly — dispatched by carta-issuance Phase 0.25.