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/pproenca/agent-tui/ralph-statusgit clone --depth 1 https://github.com/pproenca/agent-tuiWhat 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 | $0.00008 | $0.00312 |
| Opus 5 | $0.00004 | $0.00156 |
| Sonnet 5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
ralph-status 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.
What it actually says
RALPH Status Check
Display current RALPH loop status from .ralph/ directory.
Actions
- Read
.ralph/status.jsonfor machine state - Read
.ralph/TODO.mdto count completed vs remaining tasks - Show recent entries from
.ralph/progress.txt(last 10 lines) - Show recent log output from
.ralph/ralph.log(last 20 lines)
Output Format
Present a clear status report:
═══════════════════════════════════════
RALPH Status: [task-name]
═══════════════════════════════════════
Status: [running|paused|complete|max_iterations]
Iteration: [N]/[max]
Progress: [completed]/[total] tasks ([percent]%)
Started: [timestamp]
Last run: [timestamp]
## Completed Tasks
- [x] Task 1
- [x] Task 2
## Remaining Tasks
- [ ] Task 3
- [ ] Task 4
## Recent Progress Log
[last 10 lines from progress.txt]
## Recent Output
[last 20 lines from ralph.log]
If No RALPH Loop Exists
If .ralph/ directory doesn't exist, inform the user:
"No RALPH loop found. Use /ralph-init to create one."
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.
- 3d ago First seen · 54 lines · 8 tokens per session scan A ab84e61d9b6e
ralph-status is a command published in the GitHub repository pproenca/agent-tui (114 stars, last pushed 4d ago), licensed MIT. It adds 8 tokens to every session and 312 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
vps-convex-fn
Gunakan skill ini saat membuat atau memodifikasi Convex functions untuk project ini.
vps-cr
Drive the local vps-cr CLI from Claude Code — start/stop, doctor, config, device approval (acc/list/revoke), status, secret. Usage: /vps-cr [args], e.g. /vps-cr --acc or /vps-cr doctor --fix.
vps-page
Gunakan skill ini saat membuat atau memodifikasi halaman dashboard.
vps-prd
Gunakan skill ini untuk mendapatkan konteks PRD tanpa membaca seluruh file 1400 baris. Jika butuh detail spesifik, baca section yang relevan dari PRD.md.
vps-action
Gunakan skill ini saat menambahkan action baru ke pipeline executor.
vps-collector
Gunakan skill ini saat membuat atau memodifikasi collector di agent/src/collectors/.