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 skills add sergei-aronsen/claude-code-toolkit --skill domain-expert-simulationgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/skills/sergei-aronsen/claude-code-toolkit/domain-expert-simulation)<a href="https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/domain-expert-simulation"><img src="https://agentmods.dev/badge/skills/sergei-aronsen/claude-code-toolkit/domain-expert-simulation.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01037 |
| Opus 5 | $0.00020 | $0.00518 |
| Sonnet 5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
domain-expert-simulation 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 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.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Expert Simulation
Why this skill exists
Non-programmer cannot do code review themselves. They lack domain expertise to spot what's missing. Simulating a Senior practitioner mid-review compensates: Claude has seen the patterns AND the failure modes.
This is NOT performance theater ("look how thorough we are"). It's a structured search for what's wrong.
When this skill activates
- Before
/gsd-shipon auth, payments, infra, security, or privacy changes - After implementation but before merging to main
- When change touches a domain user is not expert in
- When user says: "is this safe", "review my", "can you check", "что я пропустил"
The pattern
- Identify the domain — most relevant Senior role
- Frame the simulation — "You are Senior X with 10 years experience. You have been burned by these mistakes."
- Ask the killer question — "What would make you reject this PR?"
- Listen to the answer — don't defend, fix.
Domain killer questions
Auth / security
- What attack vectors did this NOT consider? Token replay? CSRF? Rate-limit bypass?
- If a hostile user finds this endpoint, what's the worst case?
- Is the failure mode safe (deny by default) or unsafe (allow by default)?
Payments
- What happens on partial failure? Money taken but order not created?
- Idempotency — what if user clicks twice?
- Decimal arithmetic correct? Or float-rounding bug?
- Refund flow — chargebacks, disputes, fraud — covered?
Database / migrations
- Will this lock the table on a 100M-row prod DB?
- If migration fails halfway — automatic rollback or manual?
- Indexes BEFORE or AFTER the column? (BEFORE = table lock)
- Backwards-compat for old API clients during deploy?
Infrastructure / scaling
- What breaks at 10× current load? 100×?
- Single point of failure — where?
- Cache invalidation — eventual consistency OK or strict required?
- Cross-region: latency, data residency, GDPR?
Privacy / compliance
- Does this log PII anywhere (Sentry, Posthog, app logs)?
- GDPR right-to-be-forgotten — can user data actually be purged?
- Cross-border data transfer — Schrems II compliant?
- Cookie consent — does this trigger?
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 · 135 lines · 40 tokens per session scan A 961971a3ad31
domain-expert-simulation is a skill published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 1,037 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.