list

list is a command for coding agents from gf-labs/ramp. It costs 13 tokens per session (607 once invoked), scanned A, original, MIT.

A read-only command that displays all available learning topics and the user's progress. It groups topics and shows whether each one has been started and, when available, its level, experience points, and review status.

In plain words
What is it for?
Use it to browse the topic catalogue and review personal learning progress without changing anything.
Why use it?
It provides one place to see what can be learned and where progress has already begun.

Command

Part of the ramp plugin — 11 commands, 2 hooks 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/gf-labs/ramp/list
Clone the repo
git clone --depth 1 https://github.com/gf-labs/ramp

Or install ramp, the plugin that ships this one along with the rest of its 11 commands, 2 hooks.

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 list

README.md
[![agentmods](https://agentmods.dev/badge/commands/gf-labs/ramp/list.svg)](https://agentmods.dev/commands/gf-labs/ramp/list)
Your own site
<a href="https://agentmods.dev/commands/gf-labs/ramp/list"><img src="https://agentmods.dev/badge/commands/gf-labs/ramp/list.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 607 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 $0.00013 $0.00607
Opus 5 $0.00006 $0.00303
Sonnet 5 $0.00003 $0.00121
Haiku 4.5 $0.00001 $0.00061

Measured 3d ago against content hash 87007ea3507a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

list 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 3d 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.

commands/list.md · 36 lines

What it actually says

Context

Topic catalog (catalog ⟕ your progress, personal layer): !python3 "$CLAUDE_PLUGIN_ROOT/ramp_core.py" catalog 2>/dev/null || echo "CATALOG_UNAVAILABLE"


Your role

Render the topic catalog above as a grouped, read-only list. This is a viewer: no writes, no questions, no inference.

The catalog is a JSON array; each entry has: name, description, node_count, group (core/sub/standalone), sources (for core), started (bool), and summary ({level, xp, due, counts} when started, else null).

If the line is CATALOG_UNAVAILABLE or empty: the CLI shim could not run — either $CLAUDE_PLUGIN_ROOT isn't set (a manual-copy install without ramp_core.py) or python3 3.8+ isn't on the PATH. Say "Couldn't read the topic catalog — check that python3 3.8+ is installed. Run /ramp:help for orientation, or /ramp:up <topic> to start a topic." and stop.

Layout:

  1. Header: ## ramp topics
  2. Core section — each group: "core" topic on one line: [mark] [name padded] [description] [progress]
    • [mark] = if started, else ·
    • [progress] = if started: [level] · [xp] XP · [due] due (use summary.level, summary.xp, summary.due; show · N due only when due > 0); if not started: [node_count] nodes · not started
    • Under a core topic, add an indented line listing its sources: └ covers [sources joined by " · "] (each also startable individually)
  3. Standalone section — each group: "standalone" topic, same one-line format. Do not print a separate flat list of sub topics — they are shown nested under their composite in step 2. (If a sub topic has its own started graph, it still appears nested; its progress is not double-counted.)
  4. Footer, verbatim: → /ramp:up <topic> to start · /ramp:tree <topic> to view · /ramp:help if you're new

Keep it tight — one screen. Preserve the catalog's ordering within each group.

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. 3d ago First seen · 36 lines · 13 tokens per session scan A 87007ea3507a

Subscribe to this mod's changes

list is a command published in the GitHub repository gf-labs/ramp (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 607 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.