fort-harden

fort-harden is a command for coding agents from djadmin/fort. It costs 16 tokens per session (371 once invoked), scanned A, original, MIT.

A guided Mac security audit and repair command. It checks your system, shows which safe fixes are available, and asks for approval before changing anything.

In plain words
What is it for?
Use it to audit Mac security settings, preview individual fixes, apply only approved fixes, and confirm that those changes worked.
Why use it?
It helps you understand security problems without applying risky changes automatically. You can review each proposed command and verify the result afterward.

Command

Part of the fort plugin — 1 skill, 3 commands shipped together

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.

agentmods
npx agentmods add commands/djadmin/fort/fort-harden
Clone the repo
git clone --depth 1 https://github.com/djadmin/fort

Or install fort, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 fort-harden

README.md
[![agentmods](https://agentmods.dev/badge/commands/djadmin/fort/fort-harden.svg)](https://agentmods.dev/commands/djadmin/fort/fort-harden)
Your own site
<a href="https://agentmods.dev/commands/djadmin/fort/fort-harden"><img src="https://agentmods.dev/badge/commands/djadmin/fort/fort-harden.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00016 $0.00371
Opus 5 $0.00008 $0.00186
Sonnet 5 $0.00003 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 5d ago against content hash 51644b9c9048, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fort-harden scanned grade A 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 5d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`fort --only <approved-ids> --fix` (sudo may prompt for a password — that's expected).

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

plugin/commands/fort-harden.md · 29 lines

What it actually says

Audit this Mac and guide the user through fixing what's safe — with explicit approval before any change. This command can modify system settings, so move carefully.

  1. Audit first: fort --json (or fort --only $ARGUMENTS --json if IDs were given).
  2. Identify the fixable failing checks (fixable: true, status: fail). Present them as a short list, each with a one-line reason it matters and what fixing it would affect. Leave judgment-call items (admin rights, antivirus, OS upgrade) out of the fix list — explain those and let the user decide.
  3. For each fix the user is interested in, run fort --only <id> --dry-run and show the exact command fort would run. Let them see it before it happens.
  4. Get an explicit yes for the specific checks. Then apply exactly those: fort --only <approved-ids> --fix (sudo may prompt for a password — that's expected). Never expand beyond what they approved, and never fix everything implicitly.
  5. Re-run fort --only <ids> --json to confirm each change took effect, and report what changed.
  6. Respect the user's setup: if they say they use SSH, need an admin account, etc., do not push to change it. Their workflow wins over a generic checklist.

Use reference/checks.md from the fort skill for the trade-offs of each fix.

$ARGUMENTS

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. 5d ago First seen · 29 lines · 16 tokens per session scan A 51644b9c9048

Subscribe to this mod's changes

fort-harden is a command published in the GitHub repository djadmin/fort (78 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 371 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.