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 skills/rubenmarcus/ralph-starter/ralph-githubnpx skills add rubenmarcus/ralph-starter --skill ralph-githubgit clone --depth 1 https://github.com/rubenmarcus/ralph-starterWhat 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 | $0.00215 |
| Opus 5 | $0.00008 | $0.00108 |
| Sonnet 5 | $0.00003 | $0.00043 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
ralph-github 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.
What it actually says
Fetch specs from GitHub issues or PRs and run an autonomous coding loop to implement them.
-
Use
ralph_fetch_specwithsource: "github"to preview the issue/PR:identifier: repo URL,"owner/repo#123", or issue URL- Use
projectto filter by repo,labelto filter by label
-
Use
ralph_runto build from the spec:- Set
from: "github"and provideproject(owner/repo) - Optionally filter with
label(e.g., "good first issue", "bug") - Set
auto: true,commit: true,validate: truefor full automation
- Set
-
For batch processing multiple issues, use
ralph_runwithauto: true— each issue gets its own branch and PR.
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 · 18 lines · 15 tokens per session scan A 463cd214e41e
ralph-github is a skill published in the GitHub repository rubenmarcus/ralph-starter (106 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 215 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 2026-08-30.
Other skills, from other repositories
develop
Project conventions and recurring gotchas for implementer agents working on agent-orchestrator. Use before committing any change in orchestrator/, tests/, or docs/.
review
Review checklist for reviewer agents on agent-orchestrator PRs. Use when evaluating a developer-produced branch before approval or change-requests.
gh-stars-classifier
Classify the user's GitHub starred repositories into semantic categories and add them to GitHub Lists. Use when the user asks to organize, classify, categorize, or clean up their GitHub stars.
create-pr
Create GitHub pull requests with Conventional Commits-formatted titles and structured PR bodies. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.