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 adtn0810/truestack --skill truestack-application-securitygit clone --depth 1 https://github.com/adtn0810/truestackWrote 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/adtn0810/truestack/truestack-application-security)<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.
<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>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 | $0.00254 | $0.02869 |
| Opus 5 | $0.00127 | $0.01435 |
| Sonnet 5 | $0.00051 | $0.00574 |
| Haiku 4.5 | $0.00025 | $0.00287 |
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.
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.
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.
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 · 162 lines · 254 tokens per session scan B e0d89bfb1624
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.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.