harden

harden is a command for coding agents from nobodyohm-web/Thot. It costs 17 tokens per session (200 once invoked), scanned A, original, MIT.

A command for fixing a numbered security finding and proving the fix with an automated test.

In plain words
What is it for?
Use it to investigate a finding through its callers, write a reproducing test, apply a correction, and verify that the change does not break other tests.
Why use it?
It makes the failure reproducible first, confirms that the test fails, then checks that the fix passes both the test and the full test suite.

Command

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/nobodyohm-web/thot/harden
Clone the repo
git clone --depth 1 https://github.com/nobodyohm-web/Thot

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/nobodyohm-web/thot/harden.svg)](https://agentmods.dev/commands/nobodyohm-web/thot/harden)
Your own site
<a href="https://agentmods.dev/commands/nobodyohm-web/thot/harden"><img src="https://agentmods.dev/badge/commands/nobodyohm-web/thot/harden.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 200 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 $0.00017 $0.00200
Opus 5 $0.00009 $0.00100
Sonnet 5 $0.00003 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 3d ago against content hash 714242a0bf92, 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 3d 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.

commands/harden.md · 19 lines

What it actually says

Corrige le finding n°$1 de la dernière liste /audit.

L'ordre compte :

  1. Relis le code avec read_file — pas seulement la ligne du sink, la fonction entière et ses appelants (callers).
  2. Écris d'abord un test qui échoue et qui reproduit le scénario d'échec décrit dans le finding. Lance-le, montre-moi qu'il échoue.
  3. Corrige. Relance le test, montre-moi qu'il passe.
  4. Relance la suite complète pour vérifier que rien d'autre n'a cassé.

Si le finding s'avère être un faux positif pendant l'étape 1, arrête-toi et dis-le : /verdict $1 refute <raison> sera la bonne suite, pas un correctif.

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. 3d ago First seen · 19 lines · 17 tokens per session scan A 714242a0bf92

Subscribe to this mod's changes

harden is a command published in the GitHub repository nobodyohm-web/Thot (0 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 200 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 2026-08-31.