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 skills add jmagly/aiwg --skill ralph-statusgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/skills/jmagly/aiwg/ralph-status)<a href="https://agentmods.dev/skills/jmagly/aiwg/ralph-status"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-status/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/skills/jmagly/aiwg/ralph-status"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-status.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 | $0.00012 | $0.00834 |
| Opus 5 | $0.00006 | $0.00417 |
| Sonnet 5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade C, and why
ralph-status scanned grade C 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. Delete and start fresh: rm -rf .aiwg/ralph/ How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Al Status
Check the status of agent loops.
Usage
/ralph-status # Current loop status
/ralph-status --verbose # Detailed iteration history
/ralph-status --latest # Show latest completion report
/ralph-status --all # List all completion reports
Your Actions
Default (Current Loop)
- Read
.aiwg/ralph/current-loop.json - Display status summary
If active loop exists:
Agent Loop: ACTIVE
Task: {task}
Completion: {completion}
Progress: {current}/{max} iterations
Duration: {elapsed}
Status: {running | paused}
Last iteration:
Result: {result}
Learnings: {learnings}
Use /ralph-resume to continue or /ralph-abort to stop.
If no active loop:
No active agent loop.
Use /ralph "task" --completion "criteria" to start one.
--verbose
Include full iteration history:
Agent Loop: ACTIVE
Task: {task}
Completion: {completion}
Progress: {current}/{max} iterations
Iteration History:
| # | Time | Action | Result | Learnings |
|---|------|--------|--------|-----------|
| 1 | 10:30 | Initial attempt | 3 failures | Need auth mocks |
| 2 | 10:32 | Added mocks | 1 failure | Date edge case |
| 3 | 10:34 | Fixed date | In progress... | - |
--latest
Read and display most recent completion report:
- Find latest
completion-*.mdin.aiwg/ralph/ - Display contents
--all
List all completion reports:
Agent Loop History
| Date | Task | Status | Iterations |
|------|------|--------|------------|
| 2025-01-15 10:45 | Fix auth tests | SUCCESS | 3 |
| 2025-01-14 15:20 | Migrate to ESM | SUCCESS | 8 |
| 2025-01-13 09:00 | Add coverage | MAX_ITER | 10 |
View report: /ralph-status --report 2025-01-15
State File Location
- Current loop:
.aiwg/ralph/current-loop.json - Iterations:
.aiwg/ralph/iterations/ - Reports:
.aiwg/ralph/completion-*.md
Error Handling
No state directory:
Al has not been used in this project yet.
Get started with:
/ralph "your task" --completion "verification command"
Or:
/ralph --interactive
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.
- 9d ago First seen · 135 lines · 12 tokens per session scan C 6f07d3fe60b7
ralph-status is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 834 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.