hoangsonww/Claude-Code-Agent-Monitor

"name": "claude-code-agent-monitor-plugins",   "description": "Official Claude Code plugin marketplace for CCAM with 14 plugins, 66 skills, 18 agents, 34 commands, and comprehensive local dashboard operations.",   "owner": { "name": "hoangs

"description": "Official Claude Code plugin marketplace for CCAM with 14 plugins, 66 skills, 18 agents, 34 commands, and comprehensive local dashboard operations.",   "owner": { "name": "hoangsonww", "url": "https://github.com/hoangsonww" }

"owner": { "name": "hoangsonww", "url": "https://github.com/hoangsonww" },

"name": "ccam-config",       "source": "./plugins/ccam-config",       "description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers

"source": "./plugins/ccam-config",       "description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the pe

"description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project memory store. Surfaces sprawl, 

"name": "ccam-cost-guard",       "source": "./plugins/ccam-cost-guard",       "description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a 

"source": "./plugins/ccam-cost-guard",       "description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end

"description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from the daily trend, surfaces the pric

"name": "ccam-quality",       "source": "./plugins/ccam-quality",       "description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUs

"source": "./plugins/ccam-quality",       "description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with

"description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with error-budget reporting, all derived from 

"name": "ccam-workflows",       "source": "./plugins/ccam-workflows",       "description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent

"source": "./plugins/ccam-workflows",       "description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence A

"description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence API at http://localhost:4820. Maps parent→chi

"description": "Deep analytics and monitoring for Claude Code sessions — cost tracking, token usage breakdowns, usage trends, and productivity scoring powered by Agent Monitor.",   "version": "2.4.5",   "author": { "name": "Son Nguyen", "ur

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

{             "type": "command",             "command": "jq -r '{session_id: .session_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json' -d @-

"type": "command",             "command": "jq -r '{session_id: .session_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json' -d @- > /dev/null 2

"command": "jq -r '{session_id: .session_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json' -d @- > /dev/null 2>&1 || true"

{             "type": "command",             "command": "jq -r '{session_id: .session_id, agent_id: .agent_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: ap

"type": "command",             "command": "jq -r '{session_id: .session_id, agent_id: .agent_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json

"command": "jq -r '{session_id: .session_id, agent_id: .agent_id, stop_reason: .stop_reason, timestamp: now | todate}' | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json' -d @- > /dev/null 2>&1 || tru

All data comes from the Agent Monitor API at `http://localhost:4820`:

All data comes from the Agent Monitor API at `http://localhost:4820`:

{   "name": "ccam-config",   "description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project me

"name": "ccam-config",   "description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project memory

"description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project memory store. Surfaces sprawl, 

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

Produce a complete, data-backed audit of how the user's `~/.claude` configuration has grown, what overlaps, and what is risky — all read through the Agent Monitor dashboard at `http://localhost:4820`.

Produce a complete, data-backed audit of how the user's `~/.claude` configuration has grown, what overlaps, and what is risky — all read through the Agent Monitor dashboard at `http://localhost:4820`.

the Agent Monitor dashboard at `http://localhost:4820`.

the Agent Monitor dashboard at `http://localhost:4820`.

- Sizes in KB; any cost in USD to 4 decimals; use ▲/▼ for scope deltas. - Cite only fields the API returned — never fabricate counts or commands. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- Sizes in KB; any cost in USD to 4 decimals; use ▲/▼ for scope deltas. - Cite only fields the API returned — never fabricate counts or commands. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- Cite only fields the API returned — never fabricate counts or commands. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- Cite only fields the API returned — never fabricate counts or commands. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Catalogue every Claude Code hook the user has configured and assess its safety — read through the Agent Monitor dashboard at `http://localhost:4820`.

Catalogue every Claude Code hook the user has configured and assess its safety — read through the Agent Monitor dashboard at `http://localhost:4820`.

read through the Agent Monitor dashboard at `http://localhost:4820`.

read through the Agent Monitor dashboard at `http://localhost:4820`.

Explorer; edit them in the `file` named by the source, then reinstall with   the dashboard's hook setup if needed. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Explorer; edit them in the `file` named by the source, then reinstall with   the dashboard's hook setup if needed. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

the dashboard's hook setup if needed. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

the dashboard's hook setup if needed. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Inventory and audit every Model Context Protocol server the user has configured — both user-scope and project-scope — read through the Agent Monitor dashboard at `http://localhost:4820`.

Inventory and audit every Model Context Protocol server the user has configured — both user-scope and project-scope — read through the Agent Monitor dashboard at `http://localhost:4820`.

dashboard at `http://localhost:4820`.

dashboard at `http://localhost:4820`.

concurrently by the running CLI); edit their definitions in the source file   named by `source`. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

concurrently by the running CLI); edit their definitions in the source file   named by `source`. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

named by `source`. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

named by `source`. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Curate the user's file-based agent memory: the long-form CLAUDE.md files plus the per-project auto-memory store — read through the Agent Monitor dashboard at `http://localhost:4820`.

Curate the user's file-based agent memory: the long-form CLAUDE.md files plus the per-project auto-memory store — read through the Agent Monitor dashboard at `http://localhost:4820`.

`http://localhost:4820`.

`http://localhost:4820`.

curl -s -X PUT http://localhost:4820/api/cc-config/file \

curl -s -X PUT http://localhost:4820/api/cc-config/file \

curl -s -X DELETE http://localhost:4820/api/cc-config/file \

curl -s -X DELETE http://localhost:4820/api/cc-config/file \

- Sizes in KB; timestamps as relative age; use ▲ for oversized / stale flags. - Cite only fields the API returned — never invent facts, names, or sizes. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- Sizes in KB; timestamps as relative age; use ▲ for oversized / stale flags. - Cite only fields the API returned — never invent facts, names, or sizes. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- Cite only fields the API returned — never invent facts, names, or sizes. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- Cite only fields the API returned — never invent facts, names, or sizes. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Map every skill available to the user — both their own (user/project scope) and the ones contributed by installed plugins — read through the Agent Monitor dashboard at `http://localhost:4820`.

Map every skill available to the user — both their own (user/project scope) and the ones contributed by installed plugins — read through the Agent Monitor dashboard at `http://localhost:4820`.

dashboard at `http://localhost:4820`.

dashboard at `http://localhost:4820`.

- Note: plugins are read-only via the Config Explorer; manage them with the   Claude Code plugin commands, not this dashboard. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- Note: plugins are read-only via the Config Explorer; manage them with the   Claude Code plugin commands, not this dashboard. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell

Claude Code plugin commands, not this dashboard. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

Claude Code plugin commands, not this dashboard. - If the dashboard is unreachable at `http://localhost:4820`, say so and tell   the user to start it with `npm start` from the repo root.

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

- If the dashboard is unreachable at `http://localhost:4820`, say so and tell

{   "name": "ccam-cost-guard",   "description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from t

"name": "ccam-cost-guard",   "description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from the d

"description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from the daily trend, surfaces the pric

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

{             "type": "command",             "command": "jq -c '{event_type: \"Stop\", session_id: .session_id, stop_reason: .stop_reason, timestamp: (now | todate)}' 2>/dev/null | curl -s -X POST http://localhost:4820/api/hooks/event -H 'C

"type": "command",             "command": "jq -c '{event_type: \"Stop\", session_id: .session_id, stop_reason: .stop_reason, timestamp: (now | todate)}' 2>/dev/null | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: a

"command": "jq -c '{event_type: \"Stop\", session_id: .session_id, stop_reason: .stop_reason, timestamp: (now | todate)}' 2>/dev/null | curl -s -X POST http://localhost:4820/api/hooks/event -H 'Content-Type: application/json' -d @- > /dev/n

curl -s -X POST http://localhost:4820/api/alerts/rules \

curl -s -X POST http://localhost:4820/api/alerts/rules \

"description": "Direct MCP integration with the Claude Code Agent Monitor dashboard — real-time session data access, quick stats, and dashboard health monitoring via Model Context Protocol.",   "version": "2.4.5",   "author": { "name": "Son

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

### 1. API Server - Reachable at `http://localhost:4820`? Response time?

### 1. API Server - Reachable at `http://localhost:4820`? Response time?

- Reachable at `http://localhost:4820`? Response time?

- Reachable at `http://localhost:4820`? Response time?

For each route, issue a single `GET` against `http://localhost:4820<path>` with a

For each route, issue a single `GET` against `http://localhost:4820<path>` with a

"description": "Developer tools for Claude Code Agent Monitor — session debugging, hook diagnostics, data export, and system health checks for maintaining a healthy monitoring setup.",   "version": "2.4.5",   "author": { "name": "Son Nguyen

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

2. **Fetch data** from `http://localhost:4820`:

2. **Fetch data** from `http://localhost:4820`:

curl -sf http://localhost:4820/api/health

curl -sf http://localhost:4820/api/health

curl -sf http://localhost:4820/api/stats

curl -sf http://localhost:4820/api/stats

curl -sf http://localhost:4820/api/sessions?limit=1

curl -sf http://localhost:4820/api/sessions?limit=1

curl -sf http://localhost:4820/api/events?limit=1

curl -sf http://localhost:4820/api/events?limit=1

curl -sf http://localhost:4820/api/analytics

curl -sf http://localhost:4820/api/analytics

curl -sf http://localhost:4820/api/pricing

curl -sf http://localhost:4820/api/pricing

curl -sf http://localhost:4820/api/settings/info

curl -sf http://localhost:4820/api/settings/info

curl -sf http://localhost:4820/api/health

curl -sf http://localhost:4820/api/health

echo '{"hook_type":"test","session_id":"diag-test","data":{}}' | \   curl -sf -X POST http://localhost:4820/api/hooks/event \

echo '{"hook_type":"test","session_id":"diag-test","data":{}}' | \   curl -sf -X POST http://localhost:4820/api/hooks/event \

curl -sf -X POST http://localhost:4820/api/hooks/event \

curl -sf -X POST http://localhost:4820/api/hooks/event \

curl -sf http://localhost:4820/api/stats

curl -sf http://localhost:4820/api/stats

curl -sf http://localhost:4820/api/events?limit=5

curl -sf http://localhost:4820/api/events?limit=5

1. **Identify the target session**:    - If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`

1. **Identify the target session**:    - If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`

- If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`

- If session ID given: `GET /api/sessions/{id}` from `http://localhost:4820`

"description": "AI-powered insights for Claude Code — pattern detection, anomaly alerting, optimization recommendations, and session comparison using Agent Monitor analytics.",   "version": "2.4.5",   "author": { "name": "Son Nguyen", "url"

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

1. **Fetch baseline data** from `http://localhost:4820`:

1. **Fetch baseline data** from `http://localhost:4820`:

1. **Gather optimization data** from `http://localhost:4820`:

1. **Gather optimization data** from `http://localhost:4820`:

1. **Identify sessions to compare**:    - If two IDs given: fetch both from `http://localhost:4820/api/sessions/{id}`

1. **Identify sessions to compare**:    - If two IDs given: fetch both from `http://localhost:4820/api/sessions/{id}`

- If two IDs given: fetch both from `http://localhost:4820/api/sessions/{id}`

- If two IDs given: fetch both from `http://localhost:4820/api/sessions/{id}`

"description": "Manage CCAM alert rules, universal webhook providers, browser push notifications, and SSH Remote Data Sources with explicit mutation and external-send confirmation.",   "version": "2.4.5",   "author": { "name": "Son Nguyen",

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

ccam remote-sources rm <id> --purge \

ccam remote-sources rm <id> --purge \

"description": "Administer CCAM's Claude Code and Codex configuration explorers, provider-aware history import, backup restore, hook installation, home directories, updates, and MCP server.",   "version": "2.4.5",   "author": { "name": "Son

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"description": "Productivity workflows for Claude Code — daily standups, weekly reports, sprint summaries, and intelligent workflow optimization powered by Agent Monitor session data.",   "version": "2.4.5",   "author": { "name": "Son Nguye

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

1. **Fetch recent session data** from `http://localhost:4820`:

1. **Fetch recent session data** from `http://localhost:4820`:

1. **Fetch sprint data** from `http://localhost:4820`:

1. **Fetch sprint data** from `http://localhost:4820`:

1. **Fetch weekly data** from `http://localhost:4820`:

1. **Fetch weekly data** from `http://localhost:4820`:

{   "name": "ccam-quality",   "description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with error-budge

"name": "ccam-quality",   "description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with error-budget re

"description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with error-budget reporting, all derived from 

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

- Cite exact `session_id`, `model`, `timestamp`, and `summary` values — never invent a cause not supported by the payload; bucket as "Other" when unclear. - End with the dominant cause and a concrete mitigation (e.g., back off and retry on 

- Cite exact `session_id`, `model`, `timestamp`, and `summary` values — never invent a cause not supported by the payload; bucket as "Other" when unclear. - End with the dominant cause and a concrete mitigation (e.g., back off and retry on 

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Cite exact `event_type`, `tool_name`, and `session_id` values — never fabricate counts. - End with the one failure pattern most worth investigating and a concrete next step. - Read-only: only report what the API returns. If `curl` cannot 

- Cite exact `event_type`, `tool_name`, and `session_id` values — never fabricate counts. - End with the one failure pattern most worth investigating and a concrete next step. - Read-only: only report what the API returns. If `curl` cannot 

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Cite exact `event_type` counts and `session_id` values — never fabricate. - End with an overall verdict (e.g., "4/4 checks passed" or "hook delivery DEGRADED") and the single highest-impact remediation (e.g., reinstall hooks via the dashb

- Cite exact `event_type` counts and `session_id` values — never fabricate. - End with an overall verdict (e.g., "4/4 checks passed" or "hook delivery DEGRADED") and the single highest-impact remediation (e.g., reinstall hooks via the dashb

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- List the specific session IDs that contributed most to any regression. - End with the single highest-priority regression and a concrete next step (and, if armed, the new rule's id/threshold). - Read-only **except** the explicit "arm" path

- List the specific session IDs that contributed most to any regression. - End with the single highest-priority regression and a concrete next step (and, if armed, the new rule's id/threshold). - Read-only **except** the explicit "arm" path

- Read-only **except** the explicit "arm" path, which is the only write. Never mutate alert rules otherwise. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Read-only **except** the explicit "arm" path, which is the only write. Never mutate alert rules otherwise. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Cite exact counts and `session_id` values — never fabricate numerators or denominators. - End with the SLO most at risk and the single action that would recover the most budget. - Read-only: only report what the API returns. If `curl` can

- Cite exact counts and `session_id` values — never fabricate numerators or denominators. - End with the SLO most at risk and the single action that would recover the most budget. - Read-only: only report what the API returns. If `curl` can

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

- Read-only: only report what the API returns. If `curl` cannot reach `http://localhost:4820`, tell the user to start the dashboard with `npm start` from the repo root.

"description": "Generate stakeholder-ready CCAM reports from local session, cost, reliability, and workflow data with explicit scope, evidence, and export-friendly Markdown.",   "version": "2.4.5",   "author": { "name": "Son Nguyen", "url":

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"description": "Operate dashboard-launched Claude Code and Codex runs with safe launch, follow-up, stop, resume, model discovery, and persistent run-history workflows.",   "version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "http

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"description": "Search, inspect, replay, and manage Claude Code sessions tracked by the Agent Monitor dashboard — find sessions by project, model, status, or date; reconstruct event timelines; walk transcripts turn-by-turn; roll up activity

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

{   "name": "ccam-workflows",   "description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence API at http:/

"name": "ccam-workflows",   "description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence API at http://loc

"description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence API at http://localhost:4820. Maps parent→chi

"version": "2.4.5",   "author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },   "homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"author": { "name": "Son Nguyen", "url": "https://github.com/hoangsonww" },

"homepage": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",

"repository": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",