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 commands/gf-labs/ramp/pingit clone --depth 1 https://github.com/gf-labs/rampWrote 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/commands/gf-labs/ramp/pin)<a href="https://agentmods.dev/commands/gf-labs/ramp/pin"><img src="https://agentmods.dev/badge/commands/gf-labs/ramp/pin.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 | $0.00014 | $0.01228 |
| Opus 5 | $0.00007 | $0.00614 |
| Sonnet 5 | $0.00003 | $0.00246 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade B, and why
pin scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then TOPIC="$FIRST"; else TOPIC=" How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Requested topic: $ARGUMENTS
Active topic:
!FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then echo "$FIRST"; else echo "claude-code"; fi
Today's date: !date +%Y-%m-%d
Knowledge graph (active topic):
!FIRST=$(echo "$ARGUMENTS" | awk '{print tolower($1)}'); if [ -n "$FIRST" ] && { [ -f "$HOME/.claude/ramp/schemas/$FIRST.md" ] || [ -f ".claude/knowledge-graphs/schemas/$FIRST.md" ]; }; then TOPIC="$FIRST"; else TOPIC="claude-code"; fi; cat ~/.claude/ramp/graphs/$TOPIC.md 2>/dev/null || echo "NO_TREE_FILE:$TOPIC"
Your role
Mid-session knowledge checkpoint for ramp. Work through the three steps below. Step 1 is display-only — proceed immediately. Steps 2 and 3 are interactive — wait for the user's reply before proceeding.
This command is a checkpoint, not a session close. After it completes, the session continues. Do not ask the user to run any session-close command or mark anything done.
Step 1 — Status (display only)
Read the loaded graph and render immediately — no questions:
## Pin — [topic] — [date] · Level: [level] · [XP] XP
Review due: [N nodes with next: date ≤ today] or "No nodes due"
Last saved: [updated: date from frontmatter]
If NO_TREE_FILE:[topic]: say "No knowledge graph found for [topic]. Run /ramp:up [topic] to create one." Stop.
Proceed to Step 2 immediately.
Step 2 — Node save
Scan the current conversation for evidence of demonstrated knowledge since the last save (check the updated: date from the graph as a reference point):
- Tool use patterns (Write, Edit, Bash, MCP calls, Agent launches)
- Exercises completed, configurations made, commands run
- Teaching-level explanations given (not just "I've used this")
- Artifacts created or modified
If no demonstrable activity detected: say "No new demonstrations detected." Skip to Step 3.
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.
- 4d ago First seen · 103 lines · 14 tokens per session scan B 36413aec3afd
pin is a command published in the GitHub repository gf-labs/ramp (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,228 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
atlas
Cross-project atlas with an adaptive render — ≤4 projects in scope get detail cards, more get one aligned digest line each, grouped by domain. Facets projects · sessions · memory · plans · specs · plugins · claude.md; a bare run renders all of them except plugins (opt-in, machine-global). --dir NAME|PATH anchors the…
memory-sprint
Show current sprint state from StudioMeyer Memory.
pickup
Where was I? Restores work state from the board and vault -- the in-progress ticket, its implementation state, blockers, and the relevant notes -- ending with the next command to run. (Claude Code's built-in /resume restores a past conversation; this restores the work itself.).
board
Open the greatcto admin board at http://localhost:3141 (Kanban, cost, pipeline, inbox, memory). Starts it in background if not running.
learn
Force claude-smart to extract learnings from this session now.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.