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/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-security)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-audit-security"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-security.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 | $0.00046 | $0.00949 |
| Opus 5 | $0.00023 | $0.00475 |
| Sonnet 5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
pn-audit-security 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 7d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-audit-security
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-security").
Focused security pass: audit and harden authentication, authorization, input validation, secret handling, CORS, JWT configuration, and rate limiting. No API design changes (use pn-audit-api), no performance changes (use pn-audit-performance) — security posture only.
Flow
1. Context
Check .pncore-stack.md for auth mechanism, framework, and known security constraints. If not found, ask:
- "What auth mechanism? (JWT / session cookies / API keys / OAuth)"
- "What framework? (Express/Fastify/FastAPI/Rails/other)"
2. Scope
If not specified: "Should I audit the full API surface or specific areas? (auth routes / all routes / specific files)"
3. Audit
Consult pn-core://skills/backend/reference/security-patterns.md and load get_skill("pn-auth-patterns").
Injection:
- Any raw SQL string interpolation?
db.query(\WHERE id = ${id}`)` → parameterized? - Any shell command with user input?
exec(userInput)→ use safe APIs? - Any template rendering with unsanitized user data?
Authentication:
- JWT: algorithm pinned? Never
algorithms: ['none']? - JWT: expiry set? Access tokens < 60 min?
- Password hashing: bcrypt/argon2? Not md5/sha1?
- Session tokens:
httpOnly,Secure,SameSitecookies? - Refresh token: stored as hash, not plaintext?
Authorization:
- Data queries scoped to authenticated user? No trust of client-supplied
userId? - Role/permission checks present before sensitive operations?
- IDOR (Insecure Direct Object Reference): resources fetched by ID without ownership check?
Input validation:
- Input validated at every boundary before processing?
- Enum values allowlisted? No trusting
req.body.roledirectly into DB? - File uploads: type checked, size limited, name sanitized?
Secrets:
- No hardcoded secrets in source?
.envin.gitignore?process.env/os.getenvvalidated at startup?- Are internal secrets exposed in error responses or logs?
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.
- 7d ago First seen · 101 lines · 46 tokens per session scan A 24d30f732e3b
pn-audit-security is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 949 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
gh-triage
GitHub OSS maintainer lifecycle triage, review, and approval management.
t800-start
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
t800-doctor
A command that runs a scripts-only health report for a T-800 or target plugin setup. It reports the version, profile, memory location, state, item counts, always-applied items, and recent audits.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).
t-800-factory-validate
A validation command for T-800 Factory files. It runs checks on agents and examines the graph of how those agents connect.