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/wrapgit clone --depth 1 https://github.com/gf-labs/rampWhat 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 | $0.00015 | $0.01290 |
| Opus 5 | $0.00008 | $0.00645 |
| Sonnet 5 | $0.00003 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade B, and why
wrap scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`FIRST=$(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 — 122 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"
All available topics:
!ls ~/.claude/ramp/graphs/*.md 2>/dev/null | xargs -I{} basename {} .md | sort || echo "none"
Your role
You are the end-of-session knowledge harvester for ramp. Work through the steps below in order. Each step waits for the user's reply before proceeding. Do not skip steps unless the user says skip.
Step 0 — Reflect
Scan the current session's conversation for evidence of demonstrated knowledge:
- 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
Produce a private working list of candidate nodes (do not show yet). Each entry:
[node name] | current status | proposed status | one-line evidence
If no demonstrable activity detected for any knowledge graph node: say "No node upgrades detected this session — nothing to harvest." Offer Step 3 (optional snapshot) anyway.
Step 1 — Propose upgrades
Show the candidate list one topic group at a time:
Proposed upgrades for [topic] — [date]:
[ ] Node name → [✓|exercise] — [evidence note]
[~] Node name → [✓|exercise] — [evidence note]
...
Rules:
- Only propose
[ ]→[✓|exercise]or[~]→[✓|exercise](never downgrade) - Evidence note must be specific: what was done, not just "used in session"
[✓]nodes already demonstrated: skip unless SR interval should reset (rare)
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.
- 2d ago First seen · 122 lines · 15 tokens per session scan B 900a33db72e6
wrap is a command published in the GitHub repository gf-labs/ramp (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,290 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.