Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jmagly/aiwgnpx agentmods add skills/jmagly/aiwg/ralph-configWrote 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-config)<a href="https://agentmods.dev/skills/jmagly/aiwg/ralph-config"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-config/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-config"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 259 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Privilege Escalation · line 268 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00021 | $0.02307 |
| Opus 5 | $0.00010 | $0.01154 |
| Sonnet 5 | $0.00004 | $0.00461 |
| Haiku 4.5 | $0.00002 | $0.00231 |
Grade B, and why
ralph-config scanned grade B 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 755 .aiwg/ralph/ How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill access pattern (post-kernel-pivot, 2026.5+)
Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as
/skill-nameby the platform. Reach them via:aiwg discover "<capability>" aiwg show skill <name>Only kernel-listed skills (
aiwg-doctor,aiwg-refresh,aiwg-status,aiwg-help,use,steward) are directly invokable as slash commands. See skill-discovery rule.
Al Config
View and modify Al's runtime configuration. Settings control loop behavior defaults such as iteration limits, timeouts, provider selection, and commit behavior. Changes persist to .aiwg/ralph/config.json and apply to all subsequent loops unless overridden per-invocation.
Natural Language Triggers
Users may say:
- "ralph config"
- "configure ralph"
- "ralph settings"
- "show ralph config"
- "set ralph max iterations"
- "reset ralph config"
- "apply ralph ci preset"
Parameters
Subcommand (required)
One of show, set, reset, or preset.
key (required for set)
The configuration key to change. See the configuration reference below.
value (required for set)
The new value to assign to the key.
Preset name (required for preset)
One of the built-in preset names: ci, thorough, or quick.
Configuration Reference
| Key | Default | Description |
|---|---|---|
maxIterations |
10 |
Maximum iterations before the loop halts |
timeout |
60 |
Maximum wall-clock time per loop (minutes) |
provider |
claude |
AI provider for loop iterations (claude, codex, factory, opencode) |
model |
(provider default) | Model override for the provider |
autoCommit |
true |
Commit after each successful iteration |
branch |
null |
Default branch name (null = work on current branch) |
quiet |
false |
Suppress verbose iteration output |
memory |
true |
Enable semantic memory accumulation |
crossTask |
false |
Pull relevant memories from other completed loops |
analytics |
false |
Enable iteration analytics logging |
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 · 321 lines · 21 tokens per session scan B f7b37c4c2edd
ralph-config is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 2,307 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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.