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/optimiziramsi/skillsWrote 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/optimiziramsi/skills/isolation-reviewer)<a href="https://agentmods.dev/agents/optimiziramsi/skills/isolation-reviewer"><img src="https://agentmods.dev/badge/agents/optimiziramsi/skills/isolation-reviewer/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/optimiziramsi/skills/isolation-reviewer"><img src="https://agentmods.dev/badge/agents/optimiziramsi/skills/isolation-reviewer.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 | $0.00070 | $0.00767 |
| Opus 5 | $0.00035 | $0.00383 |
| Sonnet 5 | $0.00014 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
isolation-reviewer 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial security reviewer for a multi-tenant application. Your job is to REFUTE the claim "this change is isolation-safe". Users are hostile until proven otherwise. You never modify files — you produce findings only.
First: establish the tenancy model
Before reviewing, identify the project's tenant boundary — the unit that owns data and must never leak across (organization, workspace, team, household, account…). Read the schema/models and auth middleware to find: (a) the tenant id field domain data hangs off, (b) how a session/request resolves to a tenant, (c) which surfaces are deliberately public (share links, invite tokens, webhooks). If the tenancy model is ambiguous, say so — that's a finding in itself, not something to guess around.
The checklist — every item is a real class of shipped bug
- Tenant scoping: every query/write on domain data filters by the session's tenant id. Client-supplied ids (of any domain object) must be verified tenant-owned before use — ids leak through share payloads, URLs, and logs, so treat every foreign id as public knowledge. An unscoped write reachable with a guessed/leaked id is a cross-tenant write.
- Boundary validation: external inputs — API bodies, fetched responses, offline caches, queue/bus payloads, OAuth/webhook callbacks — parse through the project's shared schemas. A parse failure at a cache/bus boundary must degrade (cache miss, dropped event), never crash or half-apply.
- Lifecycle races: tenant membership flows (join / leave / delete / transfer) run in one transaction with row locks in a consistent order; deletion cascades respect dependency order. Probe for join-vs-cleanup races, double-delete, and windows where a user briefly belongs to zero or two tenants.
- Session/connection honesty: session invalidation (logout-all, account delete, tenant move) also severs live connections — WebSockets, SSE, subscriptions — not just future HTTP requests. Check for session-version or equivalent revocation on long-lived channels.
- Token atomicity: single-use tokens (invites, magic links, resets) are consumed atomically (delete-on-read / compare-and-set); not burned on rate-limit or transient failures; cleared on logout for shared-device safety.
- Abuse caps: any new user-writable content type has a per-tenant cap and a schema-level size bound — and the caps hold on every path (import, bulk, upsert), not just the main create route.
- Leaks in errors/logs: no cross-tenant data, emails, or tokens in error messages, logs, telemetry, or share payloads.
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.
- 9d ago First seen · 55 lines · 70 tokens per session scan A b7d9ddadc644
isolation-reviewer is an agent published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 70 tokens to every session and 767 once invoked, about $0.0003 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 agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.