Skip to main content
affpapa.org
RU EN
skill CX Codex

reliability-report — Claude Code skill: report and install

This skill reviews CCAM session outcomes, hook events, alerts, and tool failures to produce a reliability report. Use it for health reviews or incident follow-up.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill reliability-report -a claude-code
Open on GitHub

What reliability-report does

The skill starts by establishing the review period and data scope. It then checks statistics, analytics, recent events, alert history, and how workflow errors propagate. Its report separates session states from API and tool errors, interrupted turns, and stale data, then tracks each issue through trigger, impact, and recovery.

It compares PreToolUse and PostToolUse counts alongside matching event context, so a count mismatch alone does not become a failure claim. The report closes with ranked corrective actions and the evidence needed to test unresolved hypotheses. It is read-only, so it does not alter the monitored data.

What it helps with

  • summarize session outcomes for a chosen review window
  • trace API errors, tool failures, and interrupted turns
  • audit hook delivery by comparing PreToolUse and PostToolUse events
  • rank corrective actions and specify evidence for open hypotheses

Example prompts for the agent

  • Prepare a CCAM reliability report for the selected period and identify the main failures.
  • Audit hook delivery by comparing PreToolUse and PostToolUse events with their context.
  • Review recent errors and rank corrective actions, including evidence needed to test open hypotheses.

How to install reliability-report

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill reliability-report -a claude-code

2Manually: put the files in place

~/.claude/skills/reliability-report/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/reliability-report/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about reliability-report

How do I install reliability-report in Claude Code?

Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill reliability-report -a claude-code, then open ~/.claude/skills/reliability-report/SKILL.md.

What does reliability-report do?

It reviews sessions, hook events, alerts, tool failures, and data freshness, then reports causes, impact, recovery, and ranked corrective actions.

Which platforms support reliability-report?

The skill is listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

Source text

SKILL.md · MIT 
---
name: reliability-report
description: >
  Generate a CCAM reliability report from session outcomes, hook events,
  alerts, tool failures, and data freshness. Use for health reviews, incident
  follow-up, hook-delivery audits, or reliability trend summaries.
---

# Reliability Report

1. Confirm the review window and data scope.
2. Read stats, analytics, recent events, alert history, and workflow error
   propagation.
3. Separate:
   - Active, waiting, completed, error, and abandoned sessions
   - API errors, tool failures, interrupted turns, and stale data
   - Trigger, impact, recovery, and remaining risk
4. Compare `PreToolUse` and `PostToolUse` counts without assuming every gap is a
   failure. Check matching event context.
5. End with ranked corrective actions and the exact evidence needed for any
   unresolved hypothesis.
6. Remain read-only.

© hoangsonww · MIT · hoangsonww/Claude-Code-Agent-Monitor

Similar skills

SKILL.md skills catalog →
find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. CX Codex +1 4,000,000installs frontend-design official anthropics This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough. 1,025,790installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. 1,219,756installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs

From the same set60

cwd-rollup Aggregates Claude Code sessions by working directory using Agent Monitor data. It compares session counts, token totals, and dollar spend across active projects. CX Codex +1 ★ 1,121repo stars run-history Inspect CCAM runs, check whether a process is still active, and connect a live run to a saved Claude Code or Codex session. CX Codex +1 ★ 1,121repo stars run-agent This skill starts Claude or Claude runs through the local CCAM Run API and keeps an eye on them from the chat. CX Codex +1 ★ 1,121repo stars workflow-report Creates workflow intelligence reports from CCAM orchestration and delegation data. Surfaces tool bottlenecks, concurrency, and context compaction. CX Codex +1 ★ 1,121repo stars executive-report Turns CCAM sessions, analytics, cost and alerts into one stakeholder report. Handy before a release or a leadership update. CX Codex +1 ★ 1,121repo stars cost-report Generates scoped CCAM token and spend reports by model, provider, source, and session. Useful for tracking agent costs and spotting unpriced usage. CX Codex +1 ★ 1,121repo stars slo-check Turns Agent Monitor events into an SLO scorecard for session completion, tool calls, and API errors. Use it to compare results with targets and track remaining error budget. CX Codex +1 ★ 1,121repo stars regression-alert Compares agent reliability this period against the last one and flags where it got worse. Handy when you need to know if things degraded. CX Codex +1 ★ 1,121repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor