truestack-application-security

truestack-application-security is a skill for Claude Code from adtn0810/truestack. It costs 254 tokens per session (2,869 once invoked), scanned B, original, MIT.

A guide for securing a self-hosted application, meaning an app that you run and maintain on your own server.

In plain words
What is it for?
It is for designing authentication and permissions, protecting passwords and sessions, validating input, preventing common web attacks, and recording security decisions.
Why use it?
It helps address risks such as stolen accounts, unauthorized access, unsafe input, request forgery, and leaked credentials.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md.

Part of the truestack plugin — 23 skills, 8 commands, 2 hooks shipped together

Good fit It is for designing authentication and permissions, protecting passwords and sessions, validating input, preventing common web attacks, and recording security decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adtn0810/truestack/truestack-application-security
Install

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.

Any agent
npx skills add adtn0810/truestack --skill truestack-application-security
Clone the repo
git clone --depth 1 https://github.com/adtn0810/truestack

Made for: Claude Code.

Or install truestack, the plugin that ships this one along with the rest of its 23 skills, 8 commands, 2 hooks.

Wrote 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.

agentmods badge for truestack-application-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-application-security/github.svg)](https://agentmods.dev/skills/adtn0810/truestack/truestack-application-security)
Your own site
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-application-security"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-application-security/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.

agentmods 80×15 button for truestack-application-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-application-security"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-application-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 254 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00254 $0.02869
Opus 5 $0.00127 $0.01435
Sonnet 5 $0.00051 $0.00574
Haiku 4.5 $0.00025 $0.00287

Measured 9d ago against content hash e0d89bfb1624, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

truestack-application-security scanned grade B with 1 finding 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

`references/hardening-reference.md`). Even on one box, `169.254.169.254` (cloud metadata) and

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/truestack-application-security/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

truestack-application-security

Security is a design property, not a checklist you bolt on at the end. The job is to make the safe path the only path: authorization that denies by default, injection that's structurally impossible, credentials that survive a database leak. On a self-hosted single server there's no WAF, no managed identity, no cloud security team — the app is the perimeter. Accuracy and honesty over a green-looking dashboard: name the real risk, don't hand-wave it.

Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult .ai/memory/ for the stack, auth model, framework, and recorded security decisions. If none exists, run truestack-project-memory. Keep the code↔memory tally balanced: an auth model, a CSP, a session strategy, a threat-model decision are architecture — record them in the same change.

Auto-research, don't recall. OWASP Top 10 rankings, NIST password/MFA minimums, CVEs, and GDPR/CCPA specifics change and are version- and date-specific — ground every such claim in an authoritative source (OWASP Cheat Sheets, NIST SP 800-63B, the current Top 10, the CVE record) before asserting it. Abstain when you can't verify; never quote a parameter or regulation from memory.

A new auth model, a session/JWT switch, or a credential-handling change is high-risk, security-touching design — route it through truestack-architecture-planning's approval gate before code. The PreToolUse gate in hooks/ is a different layer: it governs agent actions (destructive / secret / outbound calls at run time), not the app's security design — don't confuse the two.

Where this skill sits: this skill owns the security design and discipline — the threat model, the auth/authz architecture, the standing controls. It is not the one-shot SAFETY pass truestack-quality-control runs on a specific change (QC enforces per-change; here you set what QC checks against). Untrusted tool/MCP output is truestack-mcp-integration's boundary; the agent-action gate is hooks/. truestack-observability redacts PII from telemetry but defers the privacy policy to truestack-data-privacy. truestack-ci-and-delivery SHA-pins actions and runs the scan in CI, while truestack-dependency-management owns the ongoing dependency policy/lifecycle. truestack-backend-development implements the API; truestack-api-design owns the contract; truestack-architecture-planning does system design. State which seam you're on and stay on it.

Read the full file on GitHub · 162 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 162 lines · 254 tokens per session scan B e0d89bfb1624

Subscribe to this mod's changes

truestack-application-security is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 254 tokens to every session and 2,869 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.