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.
git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/ralph)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/ralph"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/ralph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/ralph"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/ralph.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00010 | $0.02692 |
| Opus 5.5 | $0.00004 | $0.01077 |
| Sonnet 5.5 | $0.00002 | $0.00538 |
| Haiku 4.5 | $0.00001 | $0.00269 |
Grade A, and why
ralph 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 yesterday.
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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Command
Autonomous development loop with Hat-lite builder/verifier system and task set isolation.
Usage
/ralph run [N] # Start loop with N iterations (default: 20)
/ralph status # Show task completion progress
/ralph init # Initialize Ralph in existing project
# Task Set Management
/ralph taskset new <name> # Create new task set and switch to it
/ralph taskset list # List all task sets with status
/ralph taskset switch <name> # Switch active task set
/ralph taskset delete <name> # Remove a task set
# Task Management
/ralph add-task "description" # Add task to current task set
# Memory Management
/ralph remember "insight" # Save learning to memories
/ralph memories # View current task set's memories
Subcommands
/ralph run [iterations]
Start the Ralph autonomous loop.
Requirements:
PROMPT.mdmust exist (created by/create-prd).ralph/current-tasksetsymlink must exist.ralph/current-taskset/tasks.jsonmust exist
Process:
- Verify required files exist
- Display loop configuration
- Execute
./ralph.sh {iterations}
Example:
/ralph run 10 # Run up to 10 iterations
/ralph run # Run up to 20 iterations (default)
/ralph status
Show current progress of the Ralph loop.
Output:
- Current task set name
- Total tasks
- Completed tasks
- Remaining tasks
- Last activity timestamp
- Current/next task
Example output:
Ralph Status
============
Task Set: initial (active)
Project: my-todo-app
Tasks: 4/6 complete (66%)
Completed:
✓ setup-001: Initialize project
✓ feat-001: Create todo list
✓ feat-002: Add todo creation
✓ feat-003: Add complete/delete
Remaining:
○ feat-004: Add localStorage
○ style-001: Apply styling
Last activity: 2026-02-01 14:30:00
/ralph init
Initialize Ralph in an existing project (without running /create-prd).
Creates:
.ralph/tasksets/initial/directory structure- Empty
.ralph/tasksets/initial/tasks.jsonwith template - Empty
.ralph/tasksets/initial/memories.md - Empty
.ralph/tasksets/initial/activity.log - Symlink
.ralph/current-taskset -> tasksets/initial - Default
PROMPT.md - Copy of
ralph.sh
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.
- yesterday First seen · 376 lines · 10 tokens per session scan A 2efbdc8700c3
ralph is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 2,692 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-16.
Other commands, from other repositories
optimize
Run the credo optimisation audit for the current repo: a freshness check, then a read-only scan (conflict hotspots, changelog fragments, test-stage convention, dogma settings, parallelism readiness, and - only if the user says Yes when asked before the scan - instruction consistency across the global and repo…
gws-tasks
List, create, complete, and manage Google Tasks.
forge-status
Show registry of all managed projects with scores, trends, and alerts.
gws-standup
Generate a standup report combining today's calendar and tasks.
p4-sprint
Plans the current sprint: pulls matching stories from the backlog, defines the sprint goal, identifies risks, and creates the sprint document. Called repeatedly at the start of each new sprint.
p4-backlog
Breaks down the features from FEATURES.md into actionable tasks, builds the prioritized backlog, and defines milestones and release planning. The result is BACKLOG.md and PROJECTPLAN.md as the steering foundation for the entire implementation.