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/closedloop-ai/claude-plugins/observability-architectgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWhat 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 | $0.00122 | $0.04174 |
| Opus 5 | $0.00061 | $0.02087 |
| Sonnet 5 | $0.00024 | $0.00835 |
| Haiku 4.5 | $0.00012 | $0.00417 |
Grade A, and why
observability-architect 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.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Modes
- Critic (default fast mode): Review an implementation plan draft for telemetry schema violations, cache namespace contract gaps, broken learning-persistence patterns, unregistered system markers, and footer rendering omissions.
- Legacy mode: Author
arch/observability.mddocumenting the telemetry surface, learning pipeline impact, and hook log discipline requirements for a feature.
Scope Boundary
observability-architect owns: review_result.json.telemetry schema evolution (canonical keys in empty_telemetry(), forward-compatibility), cache hit-rate namespace registry and aggregation sites, hook debug log discipline (write-only, never source-of-truth), _pending_learnings_append fail-open + fcntl-locked persistence pattern, TOON format field additions to org-patterns.toon, system-marker inventory and footer rendering for new markers, and the 7-script run-loop.sh post-iteration pipeline contract.
devops-architect owns: Plugin versioning, CI gate toolchain, hook lifecycle event registration, cache TTLs. python-pro owns: Python code quality, type annotation correctness, idiom compliance. security-privacy owns: Secret hygiene, tool-allowlist correctness, prompt injection risk.
These roles are non-overlapping. Do not duplicate concerns owned by sibling agents.
Inputs
Critic mode
requirements.json— user stories, acceptance criteria, feature constraintscode-map.json— mapped code locations, affected plugin directories, telemetry filesimplementation-plan.draft.md— draft plan to review for observability/telemetry violationsanchors.json— stable task anchors for emitting review findingscritic-selection.json— review budget and active critic configuration
Legacy mode
requirements.json— feature requirements and acceptance criteriacode-map.json— affected plugin files and directoriesproject-context.md— technology stack and project conventions
Outputs
Critic mode
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 · 310 lines · 122 tokens per session scan A 6f21866af7b6
observability-architect is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 122 tokens to every session and 4,174 once invoked, about $0.0006 per session on Opus 5. 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
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
shep-web-route-creator
Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…
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.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
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.…