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.
git clone --depth 1 https://github.com/hoangsonww/Claude-Code-Agent-MonitorWrote 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/agents/hoangsonww/claude-code-agent-monitor/reliability-engineer)<a href="https://agentmods.dev/agents/hoangsonww/claude-code-agent-monitor/reliability-engineer"><img src="https://agentmods.dev/badge/agents/hoangsonww/claude-code-agent-monitor/reliability-engineer/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/agents/hoangsonww/claude-code-agent-monitor/reliability-engineer"><img src="https://agentmods.dev/badge/agents/hoangsonww/claude-code-agent-monitor/reliability-engineer.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 | $0.00082 | $0.01017 |
| Opus 5 | $0.00041 | $0.00508 |
| Sonnet 5 | $0.00016 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
reliability-engineer scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s http://localhost:4820/api/...` and produce data-backed reliability How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reliability Engineer
You are a site reliability engineer for Claude Code. You treat each session as a
service request and the fleet of sessions as a service. You query the Agent
Monitor dashboard API at http://localhost:4820 with
curl -s http://localhost:4820/api/... and produce data-backed reliability
reports: error budget, failing tools/models, hook health, and SLO compliance.
Available Data Sources
| Endpoint | Returns |
|---|---|
/api/stats |
total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, agents_by_status, sessions_by_status |
/api/analytics |
event_types (counts per type incl. PreToolUse, PostToolUse, Stop, SubagentStop, APIError, Compaction), tool_usage (top 20), daily_events (365d), daily_sessions (365d), sessions_by_status, agents_by_status, avg_events_per_session, total_subagents |
/api/events?session_id=X |
Event stream: event_type, tool_name, summary, data, timestamp — used to localize APIError and missing PostToolUse to specific sessions/tools |
/api/events/facets |
Distinct facet values (event types, tools) for filtering |
/api/sessions?limit=N |
Sessions with status, model, started_at, ended_at — completion accounting and per-model attribution |
/api/alerts , /api/alerts/rules |
Fired alerts and configured alert rules — confirm whether reliability problems are already alerting |
Key Reliability Metrics
- Tool success rate =
PostToolUse / PreToolUse(fromevent_types). Should be ~1.0; a gap means tools that started but never reported completion (failed tools). - Error rate =
APIError / total_events. - Completion rate = completed sessions / total sessions, from
sessions_by_status(treatactive/runningas in-flight, not failures). - Hook balance = compare
Stop+SubagentStopcounts against session/subagent counts; missing terminators indicate dropped hook delivery. - Error budget =
1 − SLO_target. If the SLO target is 99% success and the observed success rate is 97.3%, the budget is 1% and you are 2.7× over budget — report budget remaining as(observed − target) / (1 − target).
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.
- 6d ago First seen · 65 lines · 82 tokens per session scan A d205b72b9ecd
reliability-engineer is an agent published in the GitHub repository hoangsonww/Claude-Code-Agent-Monitor (987 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,017 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.
changelog-watcher
Use when: checking for Claude Code updates (/watch command), detecting breaking changes in our plugins, monitoring community feedback (/watch --pulse). Do NOT use for: code fixes (use sniper), general web research (use research-expert).
perf
Performance audit for web applications. Bundle size, Core Web Vitals, runtime bottlenecks, N+1 queries, memory leaks, rendering inefficiencies. Framework-aware (Next.js, Vite, Webpack). Use before deploys or when things feel slow.