MARVIN is a personal AI assistant built to remember conversations, track goals, organize work, and connect to external applications. People use it as a chief-of-staff-style extension for Claude Code or GitHub Copilot CLI, with integrations including Google Workspace, Microsoft 365, Slack, Linear, Notion, and Telegram. The catalogue entries provide commands, agents, skills, and instructions that define MARVIN's workflows.
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 SterlingChin/marvin-template --skill hardengit clone --depth 1 https://github.com/SterlingChin/marvin-templateWrote 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/sterlingchin/marvin-template/harden)<a href="https://agentmods.dev/skills/sterlingchin/marvin-template/harden"><img src="https://agentmods.dev/badge/skills/sterlingchin/marvin-template/harden/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/sterlingchin/marvin-template/harden"><img src="https://agentmods.dev/badge/skills/sterlingchin/marvin-template/harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01735 |
| Opus 5 | $0.00026 | $0.00868 |
| Sonnet 5 | $0.00010 | $0.00347 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
harden 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 10d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Hardening Audit
Perform a systematic hardening audit of this project. Work through each phase below, exploring the codebase to find real issues — not hypothetical ones. For each finding, explain the risk and suggest a concrete fix.
When to Use
- When user types
/harden - When user wants to audit a project for security, test coverage, or code quality
- Before making a private repo public
- After a major feature or refactor to check for regressions
- When onboarding to an unfamiliar codebase to assess its health
Process
Step 1: Context Gathering (Phase 0)
Before scanning, ask these questions to calibrate the audit. The user can answer inline or say "skip" to assume worst-case (strictest ratings).
- Visibility — Is this repo private, or could it go public?
- Access — Just you, a team, or open source?
- Deployment — Local only, server, or cloud?
- Compliance — Any regulatory or legal requirements? (government forms, PII rules, HIPAA, etc.)
- Known issues — Areas you already know are problematic? (prioritize or skip)
Use the answers to calibrate severity ratings throughout the audit. For example:
- "Private repo, solo access" — PII in git is medium, not critical
- "Going public" — PII in git is critical
- "Government forms" — output validation is high priority
If the user skips, assume: public visibility, shared access, compliance required.
After calibration, state assumptions: Based on the answers, tell the user what this audit covers and what it doesn't. For example:
- "Covering: source code, config files, git history, dependencies, test coverage"
- "Not covering: infrastructure, CI/CD pipeline, database security, runtime monitoring"
- "Does this match your expectations, or should I adjust?"
Tailor the scope assumptions to the project. A web app with a Dockerfile gets different assumptions than a CLI tool. Let the user confirm or adjust before proceeding.
Step 2: Audit Scopes
Work through these one at a time. After each scope, summarize findings and ask if the user wants to go deeper or move to the next scope.
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.
- 10d ago First seen · 177 lines · 52 tokens per session scan A 73655b70e90e
harden is a skill published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 1,735 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.