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 commands/perniemann/pncore/pn-audit-apigit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/commands/perniemann/pncore/pn-audit-api)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-audit-api"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-api.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 | $0.00044 | $0.00989 |
| Opus 5 | $0.00022 | $0.00495 |
| Sonnet 5 | $0.00009 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
pn-audit-api 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-audit-api
Start every response with: [pn-command] 🔺
Advanced (palette-hidden). Not in the
/slash palette. Invoked by the/pn-backend-auditumbrella, or directly viaget_command("pn-audit-api").
Progress: Before each numbered section in Flow, state one line:
"pn-audit-api: Step 1 of 5 — Context.""pn-audit-api: Step 2 of 5 — Scope.""pn-audit-api: Step 3 of 5 — Audit.""pn-audit-api: Step 4 of 5 — Fix.""pn-audit-api: Step 5 of 5 — Summary."
Focused API design pass: audit and fix REST conventions, HTTP semantics, response consistency, input validation, and schema leaks. No security posture changes (use pn-audit-security), no performance changes (use pn-audit-performance) — API design only.
Flow
1. Context
Check .pncore-stack.md for known stack, API style, and auth mechanism. If not found, ask:
- "What API framework? (Express/Fastify/Hono/FastAPI/other)"
- "REST or GraphQL? Versioned (
/v1/) or unversioned?"
2. Scope
If not specified: "Which routes or modules should I audit? Or reply 'all' for full API."
3. Audit
Load get_skill("pn-openapi-design") and consult pn-core://skills/backend/reference/api-design.md.
For each route or endpoint group, audit:
Resource naming:
- Are URLs noun-based? No verbs in paths (
/createUser→/users)? - Collections plural? (
/user→/users) - Sub-resources correctly nested? No nesting > 2 levels?
HTTP method usage:
- GET is safe and idempotent? No state changes in GET handlers?
- POST used for creation only? Not for generic "do something"?
- PUT vs. PATCH: PUT for full replace, PATCH for partial update?
- DELETE idempotent? Returns 204 or appropriate on success?
Status codes:
- 200 for errors? → Fix to correct 4xx/5xx
- 201 on creation? 204 when no body to return?
- 401 vs. 403 confused? (401 = unauthenticated, 403 = forbidden)
- 400 vs. 422 confused? (400 = malformed, 422 = valid but failed validation)
Response shapes:
- Consistent envelope? (
{ data: ... }or{ data: ..., meta: ... }) - Errors have
code+message+requestId? - Raw DB rows returned? ORM model leaked with internal fields?
- Consistent date format? (ISO 8601 UTC:
2026-03-27T12:00:00Z)
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.
- 4d ago First seen · 102 lines · 44 tokens per session scan A 211d1e6bffb2
pn-audit-api is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 989 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 commands, from other repositories
t800-start
Единая команда. Создание rules, skills, commands, subagents, hooks — для плагина, текущего проекта или глобально.
t800-fix
Зачем: узкая правка существующих agents / skills / commands / rules / hooks по pack — без полного DEEP /t800-start.
t800-loop
Зачем: после прогона (report + lessons) — HITL-очередь в {memorypath}/loop-queue.md, затем batch /t800-fix по fix-packs. Не автопродолжение через stop/followup.
t800-plugin-audit
Зачем: карта agents / skills / commands / rules / hooks внутри --plugin-root (граф, orphans, alwaysApply) — без dump в KB T-800.
t800-audit
Зачем: понять, какие rules/skills/commands/agents реально нужны, а какие только едят контекст.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.