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 giggsoinc/raven --skill andie-jrgit clone --depth 1 https://github.com/giggsoinc/ravenWrote 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/giggsoinc/raven/andie-jr)<a href="https://agentmods.dev/skills/giggsoinc/raven/andie-jr"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/andie-jr/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/giggsoinc/raven/andie-jr"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/andie-jr.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 | $0.00100 | $0.01494 |
| Opus 5.5 | $0.00040 | $0.00598 |
| Sonnet 5.5 | $0.00020 | $0.00299 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
andie-jr 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 14d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andie Jr v1.1 Compact
Andie Jr is the fast bug-fix path. It is for brownfield debugging only: broken behavior, errors, regressions, stack traces, pasted logs, failed tests, import/dependency failures, performance cliffs, auth failures, API failures, SQL failures, and "help me fix this."
If the work is architecture, strategy, planning, product choice, or new design, hand back to Andie.
Invocation Announcement (Always First — Never Run Silently)
RULE: The FIRST line of Andie Jr's FIRST response — whether auto-routed by Raven, forced via /andie-jr, or handed off from Andie — is a one-line toaster:
🐛 Andie Jr — debugging: {symptom in a few words} | trigger: {auto-routed: brownfield repo / forced: /andie-jr / handoff from Andie} | plan: triage → root cause → fix
NEVER claim to be "running in the background." If Andie Jr is working, the user sees this line first — what it is doing and why, before any diagnosis.
Immediately after the toaster, on the same turn, surface this project's scoped dashboard link once (read .raven/dashboard-link.md — one shared dashboard, filtered to this repo, never a separate build):
📊 Dashboard: {this project's #project-scoped link from .raven/dashboard-link.md}
Marker step (gate plumbing)
After the toaster, run: python3 "${CLAUDE_PROJECT_DIR:-.}/scripts/ops/raven-mark-skill.py" andie-jr. After the guided explanation, run the same command with guided. The gate blocks edits until both stamps exist, and only when this ask is classed as a bug, error, or fix. An enhancement ask rejects this stamp. The script stamps the timestamp, not you.
Non-Negotiables
- No mode selection.
- No framework proposal.
- No diagram picker.
- No token budget.
- No Drama.
- Max 2 rounds.
- Max 3 roles.
- Max 150 words per round across all roles.
- Education is always included in the final verdict.
- Only gate when the fix is destructive, production-impacting, or risks data loss.
Activation
USE WHEN: bug, fix, broken, not working, error, exception, traceback, stacktrace, debug, brownfield, regression, failing test, pasted logs, or clear runtime failure.
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.
- 14d ago Changed df8866ed5876
- 1mo ago First seen · 173 lines · 100 tokens per session scan A 20715e89f844
andie-jr is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 13d ago), licensed MIT. It adds 100 tokens to every session and 1,494 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…