get

A qmd command that retrieves and prints the contents of an indexed document. qmd can locate a file by path, document ID, virtual path, or a matching suffix.

In plain words
What is it for?
Use it to read indexed Markdown, code, or other documents from the command line, including only the section beginning at a specified line.
Why use it?
It gives you the document body without opening files manually or guessing the exact location. You can also start at a chosen line and request line numbers.

Command

Part of the qmd plugin — 2 skills, 18 commands, 1 MCP server shipped together

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.

agentmods
npx agentmods add commands/ramonclaudio/skills/get
Clone the repo
git clone --depth 1 https://github.com/ramonclaudio/skills

Or install qmd, the plugin that ships this one along with the rest of its 2 skills, 18 commands, 1 MCP server.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00274
Opus 5 $0.00012 $0.00137
Sonnet 5 $0.00005 $0.00055
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash 666df39e28c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

get 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 2d 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.

plugins/qmd/commands/get.md · 25 lines

What it actually says

Run qmd get $ARGUMENTS. Prints a document body to stdout.

Path resolution order:

  1. Docid: #abc123 (6-char content hash)
  2. Virtual path: qmd://collection/path/to/file.md
  3. Collection-prefixed: next.js/docs/api.md
  4. Filesystem: absolute, ~/, or relative path
  5. Suffix match (last resort)

Useful flags:

  • file.md:N — start at line N (shorthand for --from N)
  • --from N / -l N — line offset and max lines
  • --line-numbers — prefix each line with N:

CLI prints "Document not found" on miss; the MCP get tool also suggests similar files via Levenshtein-style suffix matching, which the CLI does not.

Prefer the MCP get tool when available — it returns a resource content block that Claude Code surfaces as a document attachment, not just stdout text.

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. 2d ago First seen · 25 lines · 23 tokens per session scan A 666df39e28c8

Subscribe to this mod's changes

get is a command published in the GitHub repository ramonclaudio/skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 274 once invoked, about $0.0001 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.