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 PostHog/posthog-foss --skill auditing-llm-gateway-paritygit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/posthog/posthog-foss/auditing-llm-gateway-parity)<a href="https://agentmods.dev/skills/posthog/posthog-foss/auditing-llm-gateway-parity"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/auditing-llm-gateway-parity/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/skills/posthog/posthog-foss/auditing-llm-gateway-parity"><img src="https://agentmods.dev/badge/skills/posthog/posthog-foss/auditing-llm-gateway-parity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 72 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 73 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00097 | $0.01088 |
| Opus 5 | $0.00048 | $0.00544 |
| Sonnet 5 | $0.00019 | $0.00218 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
auditing-llm-gateway-parity 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing LLM gateway parity
Compare the current implementations of both gateways and update services/llm-gateway/PARITY.md. Keep this audit separate from caller migration.
Record source revisions
- Fetch
origin/masterand record its SHA as the PostHog baseline. - Audit the current working tree, including committed and uncommitted changes relative to that baseline. Do not ignore an in-flight gateway change because it is not on
masteryet. - Read the current
PostHog/ai-gatewaymain SHA withgh api repos/PostHog/ai-gateway/commits/mainand record it as the Go baseline. - If the audit is for an in-flight Go change, inspect that PR branch or working tree relative to
main. Treat its contracts as pending until the change merges; do not record them as currently supported. - Otherwise, inspect an authenticated checkout of
PostHog/ai-gatewayatmain.
Audit implementation code. README files and the existing parity table are starting points, not proof.
Inspect each contract
For the Python gateway, inspect:
services/llm-gateway/src/llm_gateway/api/for routes and wire behaviorservices/llm-gateway/src/llm_gateway/auth/for accepted credentialsservices/llm-gateway/src/llm_gateway/db/required_tables.pyfor the tables the gateway may read; a change adding a table read needs its posthog-cloud-infra SELECT grant landed in every environment firstservices/llm-gateway/src/llm_gateway/products/config.pyfor trusted product policy, models, and billingservices/llm-gateway/src/llm_gateway/rate_limiting/for budgets and limitsservices/llm-gateway/src/llm_gateway/callbacks/for event attributionposthog/llm/gateway_client.pyand real call sites for required contracts
For the Go gateway, inspect:
internal/httpapi/routes.goand dispatch packages for API shapesinternal/auth/andinternal/principal/for credential and identity policyinternal/httpapi/admission.go,internal/ledger/, andinternal/quota/for billing and limitsinternal/catalog/,internal/router/, andinternal/dispatch/for models, providers, translation, and failoverinternal/emitter/and request parsing for attribution and metadatadocs/product.mdfor intended and deferred contracts, verified against code
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 · 76 lines · 97 tokens per session scan A 4c59ca3ef3b8
auditing-llm-gateway-parity is a skill published in the GitHub repository PostHog/posthog-foss (715 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,088 once invoked, about $0.0005 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 skills, from other repositories
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.