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-abortgit 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-abort)<a href="https://agentmods.dev/skills/jmagly/aiwg/ralph-abort"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-abort/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-abort"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-abort.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 60 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.
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 | $0.00014 | $0.00836 |
| Opus 5.5 | $0.00006 | $0.00334 |
| Sonnet 5.5 | $0.00003 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
ralph-abort 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Al Abort
Abort a running or paused agent loop.
Usage
/ralph-abort # Abort, keep changes
/ralph-abort --revert # Abort and revert all changes
/ralph-abort --force # Abort even if no active loop
Parameters
--keep-changes (default)
Stop the loop but keep all file changes made during iterations.
--revert
Revert all changes made during the agent loop using git:
- Identify commits made during loop (prefix:
ralph: iteration) - Reset to commit before loop started
- Warning: This discards work
--force
Abort even if state indicates no active loop (for cleanup).
Your Actions
Standard Abort
- Read
.aiwg/ralph/current-loop.json - Verify there's an active loop
- Mark loop as aborted
- Generate partial completion report
- Confirm to user
Output:
Agent Loop: ABORTED
Task: {task}
Iterations completed: {N}
Duration: {time}
Changes have been kept. To revert:
git reset --hard HEAD~{N}
Partial report: .aiwg/ralph/completion-{timestamp}.md
With --revert
- Read loop state
- Find all
ralph: iterationcommits from this loop - Confirm with user before reverting
- Reset git to pre-loop state
- Clean up state files
Confirmation prompt:
This will revert {N} commits:
- ralph: iteration 1 - initial attempt
- ralph: iteration 2 - fixed auth
- ralph: iteration 3 - in progress
Files to be reverted:
- src/auth.ts
- test/auth.test.ts
Type 'yes' to confirm revert:
After revert:
Agent Loop: ABORTED + REVERTED
Reverted {N} commits.
Working directory restored to pre-loop state.
State cleaned: .aiwg/ralph/current-loop.json archived
Error Handling
No active loop:
No active agent loop to abort.
Use --force to clean up stale state files if needed.
Git not available:
Git not available for --revert option.
Loop aborted, but changes cannot be reverted automatically.
Manual cleanup may be needed.
Dirty working directory (for --revert):
Cannot revert: uncommitted changes exist.
Options:
1. Commit or stash changes first
2. Use /ralph-abort without --revert to keep current state
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.
- 1mo ago Changed 15bd350ffac7
- 1mo ago First seen · 142 lines · 14 tokens per session scan A bf163e8c2479
ralph-abort is a skill published in the GitHub repository jmagly/aiwg (225 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 836 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
gear
Managing dependencies, CI/CD, advanced GitHub Actions workflows, containers, secrets, and operational config. Use for build, workflow, or environment work.
launch
Planning releases and reporting delivery work from GitHub PR history. Use when versioning, CHANGELOGs, rollout or rollback plans, engineering metrics, retrospectives, or stakeholder reports are needed.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
trail
Investigating git history, analyzing regression root causes, and performing code archaeology. Time-travels through commits to uncover truth. Use for git history investigation.
oss-repo-maintainer
Maintain open-source repositories by checking README accuracy, version consistency, release readiness, and documentation drift. Use for: fix README, prepare release, repository maintenance, sync documentation.
missive
Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.