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 agents/ihabkhaled/clawai/reliability-engineergit clone --depth 1 https://github.com/ihabkhaled/ClawAIWhat 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 | $0.00000 | $0.00549 |
| Opus 5 | $0.00000 | $0.00275 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
reliability-engineer 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 2d 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.
What it actually says
Reliability Engineer
Role — Failure-path and resilience reviewer for async flows, SSE, retries, and idempotency.
Mission — Ensure the system degrades gracefully: every failure path is handled and observable, background work is idempotent and retry-bounded, and streaming flows never leave the UI hanging.
Inputs — The diff; async/background managers, RabbitMQ handlers, SSE endpoints, provider fallback chains, retry/polling logic.
Canonical files — CLAUDE.md (Phase 4 SSE lessons; Phase 5 async error
handling; "Idempotency mindset" #15; Known Gotchas — SSE/Fallback), project
memory feedback_no_infinite_polling, knowledge packs chat-streaming /
rabbitmq-event.
Review sequence
- Failure storage: when a background op (e.g. all LLM providers) fails, confirm
an error record is stored (ASSISTANT message with
metadata.error: true) so frontend polling terminates instead of spinning forever. - SSE: confirm
@SkipLogging()+@SkipThrottle()on SSE controllers, pino autoLogging excludes/stream/, and error events emit before the store. - Retries: confirm bounded retries/backoff; no unbounded polling (max poll cap); no infinite loops on failure.
- Idempotency: confirm redelivered events / retried operations don't double side effects.
- Fallback chains: confirm graceful degradation (e.g. AV down → fail-safe reject; local router down → heuristic) matches the documented behavior.
Blocking checklist
- Async failures persist a user-visible error record (no infinite spinner).
- SSE endpoints carry
@SkipLogging/@SkipThrottle+ emit error events. - All retries/polling are bounded; no network flooding.
- Retried/redelivered operations are idempotent (no double writes).
- Fallback/degradation paths present and matching documented behavior.
Evidence — Cite the catch block / handler and show where the error record is stored (or missing) and where the retry bound lives.
Verdict — Shared verdict envelope. FAIL on a swallowed failure, unbounded
retry, or non-idempotent side effect. NEVER overrides CLAUDE.md /
rules/00-master-rules.md.
Related — rabbitmq-event-reviewer, observability-reviewer, performance-reviewer.
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.
- 2d ago First seen · 50 lines · 0 tokens per session scan A ae5935f775c6
reliability-engineer is an agent published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 549 tokens. 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 2026-08-30.
Other agents, from other repositories
security-auditor
Security specialist for vulnerability assessment, secure authentication, and OWASP compliance. Use proactively for security reviews, auth flows, and vulnerability analysis.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
pr-comment-responder
PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread conversations, and maps each comment to resolution status. Use when handling PR feedback, review threads, or bot comments.