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/helpgit 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 | $0.00014 | $0.00752 |
| Opus 5 | $0.00007 | $0.00376 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Your state (for the dynamic top line):
!python3 "$CLAUDE_PLUGIN_ROOT/ramp_core.py" catalog 2>/dev/null | python3 -c "import sys,json; c=json.load(sys.stdin); started=[t for t in c if t['started']]; due=sum((t['summary'] or {}).get('due',0) for t in started); print(f'STARTED={len(started)} DUE={due}')" 2>/dev/null || echo "STARTED=ERR DUE=0"
Your role
Render an orientation page. Read-only: no writes, no questions.
Parse the STARTED=N DUE=M line above and open with the matching dynamic top line:
STARTED=ERR→_Couldn't run ramp's Python helper — check thatpython3**3.8+** is on yourPATH._(then render the static body below anyway — orientation works without it)STARTED=0→**You're new here.** Run/ramp:listto see topics, then/ramp:upto begin.DUE> 0 →**Welcome back — [DUE] node(s) due.** Run/ramp:reviewto keep them fresh.STARTED> 0 andDUE= 0 →**Pick up where you left off:**/ramp:up.
Then render this evergreen body verbatim (fill nothing in — it is static):
## What ramp is
ramp maps what you can *do* with Claude Code — a knowledge graph grounded in your
real environment, not a checklist. It scores `[✓]` demonstrated over `[~]`
self-reported, and keeps skills alive with spaced repetition.
## Commands
**Start**
/ramp:up <topic> Assess, build your graph, and learn — the main command
/ramp:calibrate <topic> Place yourself on a topic's tree — a worksheet seeds your graph
/ramp:check Check back your active task — grade it, save, report the XP delta
/ramp:list See every topic and where you've started
/ramp:help This 60-second orientation
**Review & reference**
/ramp:review Run spaced-repetition review of what's due
/ramp:tree <topic> View a topic's full graph
/ramp:cheatsheet Your demonstrated skills + evidence trail
**Capture**
/ramp:pin Mid-session checkpoint
/ramp:wrap End-of-session knowledge harvest
**Extend**
/ramp:ingest Generate a topic schema from a PDF, URL, or file
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 · 60 lines · 14 tokens per session scan A ccac0a9c3451
help 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 752 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.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.