ingest-markdown-report

ingest-markdown-report is a skill for Claude Code from pi-sloane/claude-plugin. It costs 38 tokens per session (430 once invoked), scanned A, original, MIT.

A tool for submitting a security report written in Markdown, a plain-text document format, to Pi Security, a security service. It accepts an inline .md or .markdown report and starts Pi's ingestion process.

In plain words
What is it for?
Use it to submit an inline Markdown security report with a valid filename after confirming the upload.
Why use it?
It provides a defined way to send a Markdown report into Pi without converting it to another format.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pi-security plugin — 6 skills, 1 MCP server shipped together

Good fit Use it to submit an inline Markdown security report with a valid filename after confirming the upload.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pi-sloane/claude-plugin/ingest-markdown-report
Install

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.

Any agent
npx skills add pi-sloane/claude-plugin --skill ingest-markdown-report
Clone the repo
git clone --depth 1 https://github.com/pi-sloane/claude-plugin

Made for: Claude Code.

Or install pi-security, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for ingest-markdown-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/pi-sloane/claude-plugin/ingest-markdown-report.svg)](https://agentmods.dev/skills/pi-sloane/claude-plugin/ingest-markdown-report)
Your own site
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 8792f96fce59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/ingest-markdown-report/SKILL.md · 36 lines

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 .md or .markdown) and content (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

  1. Validate: fileName ends in .md or .markdown, and content is non-empty Markdown within the size limit.
  2. 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.
  3. Explain the effect: Pi will store the report and start its ingestion workflow in the authenticated tenant.
  4. Ask for confirmation and proceed only on an explicit yes in the current turn.
  5. Call the tool once.
  6. 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.
  7. If the call fails or times out ambiguously, report that and stop. Do not retry automatically, since a retry could submit a duplicate report.
Changes

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.

  1. 8d ago First seen · 36 lines · 38 tokens per session scan A 8792f96fce59

Subscribe to this mod's changes

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.