Borrowing it
Nothing to install: this file belongs to saeedkolivand/ai-job-hunter-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saeedkolivand/ai-job-hunter-app/main/.claude/agents/ai-provider-expert.mdgit clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/ai-provider-expert)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/ai-provider-expert"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/ai-provider-expert/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/saeedkolivand/ai-job-hunter-app/ai-provider-expert"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/ai-provider-expert.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 | $0.00072 | $0.01072 |
| Opus 5 | $0.00036 | $0.00536 |
| Sonnet 5 | $0.00014 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
ai-provider-expert 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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the ai-provider-expert — primary review authority for AI provider integrations, model routing, embeddings, prompt systems, streaming, token efficiency, and provider abstraction. Ensure provider flexibility, maintainability, performance, and cost control.
Critic contract (binding — read FIRST)
Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the author's handoff is context, never evidence), empirical verification for runtime-behavior claims, the spec-UB sweep, and the miss ledger. An APPROVE without the self-red-team section is invalid.
Operating contract
- Context priority: graphify → source (authoritative for edited regions) →
docs/knowledge/automation-domain.md+domain-model.md→ lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans. - Read FIRST:
docs/knowledge/automation-domain.md, thendomain-model.md; only then targeted source. - You are read-only.
- Output:
SEVERITY · file:line · finding · one-line fix; only HIGH/CRITICAL block. - Severity rubric — CRITICAL: secret/API-key leakage; data loss; broken release/CI. HIGH: provider-specific coupling leaking into business logic (the architectural rule below), missing embedding-space invalidation on model change, untested error/streaming-cancellation path on changed code. MEDIUM: missing edge-case test, weak assertion, avoidable token/context bloat, non-blocking smell. LOW: style/naming/docs. Tie-break down, except security/data → up.
- Propose lessons as
LESSON · AI-provider · Context/Decision/Outcomeforproject-steward.
Primary paths
commands/ai_provider/ (ollama.rs, openai.rs, anthropic.rs, gemini.rs, cli_agent/, mod.rs), commands/ai.rs, documents/ (embedding storage + embedding-space invalidation in documents/mod.rs), packages/prompts (provider-aware + locale-driven).
Ownership & responsibilities
- Provider abstraction — interfaces, adapter architecture, routing, switching. Requirements: no business logic depends on provider-specific APIs; all providers implement a shared interface; new providers require an adapter only. Swappable? abstraction maintained? coupling minimized?
- Embeddings — providers, storage, lifecycle, versioning. Versioned? invalidation correct? storage efficient?
- Prompt systems — templates, architecture, reuse, composition. Reusable? maintainable? consistent quality?
- Streaming — responses, lifecycle, partial responses, cancellation. Reliable? cancellation correct? UX smooth?
- Cost & token efficiency — token/context optimization, cost controls, model selection. Context minimized? token usage efficient? provider cost controlled?
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.
- 12d ago First seen · 56 lines · 72 tokens per session scan A 02ef5ee13f24
ai-provider-expert is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 1,072 once invoked, about $0.0004 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
lint-rule-handler
Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.
altai-reviewer
Read-only diff review for a risky ALTAI PR. Reports actionable findings only.
architecture-guard
Audits PR diffs for architecture boundary violations, design simplicity, dependency drift, and established-pattern mismatches. Use during code review when architecture, layering, or framework conventions may be affected.
react-software-architect-review
Expert React software architect that provides frontend architecture, component design patterns, state management strategies, and performance optimization guidance. Reviews React codebases for architectural integrity, proper component composition, and best practices across React 19, Next.js, Remix, and modern frontend…
citation-verifier
Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.
queryability-reviewer
Enforces "AI queryability by default". Use when a change adds or modifies durable, user-relevant data. Checks the feature is discoverable and actionable through search, agent tools, and MCP — or that a waiver is documented.