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/bjornjee/agent-dashboard/rcanpx skills add bjornjee/agent-dashboard --skill rcagit clone --depth 1 https://github.com/bjornjee/agent-dashboardWrote 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/bjornjee/agent-dashboard/rca)<a href="https://agentmods.dev/skills/bjornjee/agent-dashboard/rca"><img src="https://agentmods.dev/badge/skills/bjornjee/agent-dashboard/rca.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.02484 |
| Opus 5 | $0.00015 | $0.01242 |
| Sonnet 5 | $0.00006 | $0.00497 |
| Haiku 4.5 | $0.00003 | $0.00248 |
Grade C, and why
rca 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 4d 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.
- `rm -rf`, `git clean`, `git reset --hard` (destructive ops) How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root cause analysis for a system-level failure. Gather ALL evidence before reasoning about the cause.
Incident description: $ARGUMENTS
Instructions
Follow these phases strictly in order. Every phase has a gate. Do not speculate about cause until Phase 5.
Phase 1: Scope the Incident
-
Parse the incident description — what died? (process, tmux server, container, service, etc.)
-
Establish the time window: ask the user or derive from context when the failure was noticed and when things last worked.
-
Identify what was running at the time — check:
tmux list-sessions/tmux list-panes -a(if tmux is back up)- Shell history with timestamps to reconstruct user activity:
tail -500 ~/.zsh_history | while IFS= read -r line; do if echo "$line" | grep -q "^: [0-9]"; then ts=$(echo "$line" | sed 's/^: \([0-9]*\):.*/\1/') cmd=$(echo "$line" | sed 's/^: [0-9]*:[0-9]*;//') dt=$(date -r "$ts" "+%Y-%m-%d %H:%M:%S" 2>/dev/null) echo "$dt $cmd" fi done - Filter to the time window around the incident.
-
Identify all active agents/processes — check Claude Code session logs:
ls -lt ~/.claude/projects/<project-dir>/*.jsonl | head -15Cross-reference modification times with the incident window.
Gate: Time window is established. List of active processes/sessions at the time is known.
Phase 2: System-Level Evidence (macOS Unified Log)
Run ALL of the following. Do not skip any — even if you expect empty results, the absence of evidence is evidence.
2a. Target process events
log show --start "<start>" --end "<end>" --style compact \
--predicate 'process == "<target-process>"'
Replace <target-process> with the crashed process (e.g., "tmux", "tmux-server", "agent-dashboard"). Run for each relevant process name.
2b. Code signature / AMFI failures
log show --start "<start>" --end "<end>" --style compact \
--predicate 'subsystem == "com.apple.AMFI" OR eventMessage CONTAINS "AMFI" OR eventMessage CONTAINS "code signature" OR eventMessage CONTAINS "CMS blob"'
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.
- 4d ago First seen · 249 lines · 30 tokens per session scan C 2d7ce2451e3e
rca is a skill published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 2,484 once invoked, about $0.0002 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
helmor-debug-operate
Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.