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-data-privacygit 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-data-privacy)<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-data-privacy"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-data-privacy/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-data-privacy"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-data-privacy.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 | $0.00252 | $0.02315 |
| Opus 5 | $0.00126 | $0.01157 |
| Sonnet 5 | $0.00050 | $0.00463 |
| Haiku 4.5 | $0.00025 | $0.00231 |
Grade A, and why
truestack-data-privacy 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
truestack-data-privacy
Personal data is a liability you must be able to find, justify, delete, and prove you deleted. This skill owns the privacy policy for a self-hosted single server: what counts as personal data, why you may hold it, how long, who may touch it, and how it leaves. On one box there is no managed compliance plane — the controls have to live in the schema and the code. Accuracy and provability over good intentions; abstain rather than assert a compliance claim you can't ground.
Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult
.ai/memory/ for the data model, stack, and which regimes apply. If none exists, run
truestack-project-memory. Keep the code↔memory tally balanced: a new data class, retention rule,
lawful basis, or purge job is a recorded decision — update memory in the same change.
Auto-research, don't recall. Regulatory and standards facts drift — never state a GDPR
article, CCPA/CPRA effective date, HIPAA Security Rule requirement, ENISA/NIST method, or
OWASP/CVE detail from memory. Ground each load-bearing claim in an authoritative source
(EDPB/ICO, the regulation text, NIST, HHS) before asserting it — the regime-specific
citations behind the rules below live in references/regimes.md; re-verify them at use time.
Defining a retention policy, a deletion pipeline, or crypto-shredding is consequential,
often irreversible work — route the design through truestack-architecture-planning's approval gate
before building. If the PreToolUse gate is wired (hooks/README.md — check it is actually
installed and active), it forces a human-yes before a hard-delete / purge / key-destruction
runs — verify that before relying on it; if it isn't wired, treat the approval as manual and
obtain the explicit human yes yourself.
Where this skill sits: it owns the privacy policy and discipline, not the mechanics of
every neighbor. truestack-quality-control runs the one-shot SAFETY pass on a change and
truestack-application-security owns the security design; this skill owns the data-handling rules
they enforce. truestack-observability redacts PII in telemetry but defers the classification and
redaction policy to here — it implements; this skill decides what is PII. truestack-mcp-integration
owns untrusted tool-output; the PreToolUse hook governs agent actions (a different layer).
truestack-backend-development implements the deletion/consent APIs (and truestack-database-migrations
authors the purge/erasure DDL + bounded backfill) but truestack-api-design owns their contract;
truestack-architecture-planning does system design.
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.
- 12d ago First seen · 136 lines · 252 tokens per session scan A 63a117f69d7c
truestack-data-privacy is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 252 tokens to every session and 2,315 once invoked, about $0.0013 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 skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.
beweislast-und-zugang-309
Für Beweislast und Zugang 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Beweislast- und Substantiierungsmatrix.
agb-pruefung-kaltstart
Für AGB Prüfung Kaltstart: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Tatbestands- oder Anspruchsmatrix.
agb-rechtswahl-schweizer-recht-rom-i
Für AGB Rechtswahl Schweizer Recht Rom I: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-rechtswahl-schweizer-recht-rom-i.