harden

harden is a command for coding agents from Goldziher/basemind. It costs 15 tokens per session (269 once invoked), scanned A, original, MIT.

A command that runs basemind's harden test harness against eight real open-source repositories. It checks scanning tools, expected results, and selected canary counts.

In plain words
What is it for?
Use it before release or after scanner changes to check pass counts, repository failures, canary searches, truncation behavior, and scan-time changes.
Why use it?
It shows whether a change still works on varied real-world code and highlights scan-time regressions or missing results.

Command

Part of the basemind plugin — 15 skills, 10 commands, 6 agents, 2 hooks, 1 MCP server 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/goldziher/basemind/harden
Clone the repo
git clone --depth 1 https://github.com/Goldziher/basemind

Or install basemind, the plugin that ships this one along with the rest of its 15 skills, 10 commands, 6 agents, 2 hooks, 1 MCP server.

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 harden

README.md
[![agentmods](https://agentmods.dev/badge/commands/goldziher/basemind/harden.svg)](https://agentmods.dev/commands/goldziher/basemind/harden)
Your own site
<a href="https://agentmods.dev/commands/goldziher/basemind/harden"><img src="https://agentmods.dev/badge/commands/goldziher/basemind/harden.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 269 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00015 $0.00269
Opus 5 $0.00008 $0.00134
Sonnet 5 $0.00003 $0.00054
Haiku 4.5 $0.00002 $0.00027

Measured 4d ago against content hash 5c8bb3a02918, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.ai-rulez/commands/harden.md · 28 lines

What it actually says

Harden

Run the harden harness (real-OSS clones + tool sweep + canaries) and summarize.

  1. Run:

    BASEMIND_HARDEN_NO_BUILD=1 \
      cargo test --release --test harden -- --ignored --nocapture \
      2>&1 | tee /tmp/basemind-harden-$(date +%s).log
    
  2. Parse the result via the harness-interpreter agent (or inline if trivial).

  3. Report:

    • Pass count: N/8 green and the names of any failed repos.
    • Canary status: tokio spawn, django get, react useState, ripgrep-shallow truncation.
    • Any per-repo scan-time delta > 20% vs the documented baseline (typescript ~23 s eager-L2-on, tokio < 2 s, django < 3 s).
  4. Exit with the harness exit code.

If the user runs /harden full, drop BASEMIND_HARDEN_NO_BUILD=1 and rebuild release first.

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. 4d ago First seen · 28 lines · 15 tokens per session scan A 5c8bb3a02918

Subscribe to this mod's changes

harden is a command published in the GitHub repository Goldziher/basemind (98 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 269 once invoked, about $0.0001 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.