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 pi-sloane/claude-plugin --skill ingest-markdown-reportgit clone --depth 1 https://github.com/pi-sloane/claude-pluginWrote 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/pi-sloane/claude-plugin/ingest-markdown-report)<a href="https://agentmods.dev/skills/pi-sloane/claude-plugin/ingest-markdown-report"><img src="https://agentmods.dev/badge/skills/pi-sloane/claude-plugin/ingest-markdown-report.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 5.1 | $0.00038 | $0.00430 |
| Opus 5 | $0.00019 | $0.00215 |
| Sonnet 5 | $0.00008 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
ingest-markdown-report 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 8d 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.
What it actually says
Submit a Markdown security report to Pi
Use this skill only when the user explicitly asks to submit or ingest a security report into Pi Security, and the report content is available inline as Markdown.
Tool
State-changing, confirmation required:
pi_report_markdown_upload- uploads Markdown report content and starts the tenant report-ingestion workflow. Inputs:fileName(must end in.mdor.markdown) andcontent(non-empty Markdown, up to 5 MiB).
Accepted input
Report content provided inline in the conversation as Markdown, plus a filename ending in .md or .markdown. If either is missing, ask for it instead of inventing one.
Rejected inputs
- Chat attachments, local file paths, and
file://URIs - PDFs, DOCX files, images, or any binary content
Those workflows belong in the Pi web app or the Sloane CLI, not this skill.
Before calling the tool
- Validate:
fileNameends in.mdor.markdown, andcontentis non-empty Markdown within the size limit. - Summarize what will be submitted - filename, approximate size, and a one-line description of the report's scope. Do not echo sensitive report content back into the conversation beyond what is needed to confirm the target.
- Explain the effect: Pi will store the report and start its ingestion workflow in the authenticated tenant.
- Ask for confirmation and proceed only on an explicit yes in the current turn.
- Call the tool once.
- Report exactly the upload and workflow state Pi returned. Queued or started means ingestion is in progress, not that findings exist yet. Never invent ingestion results.
- If the call fails or times out ambiguously, report that and stop. Do not retry automatically, since a retry could submit a duplicate report.
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.
- 8d ago First seen · 36 lines · 38 tokens per session scan A 8792f96fce59
ingest-markdown-report is a skill published in the GitHub repository pi-sloane/claude-plugin (12 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 430 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.