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.
git clone --depth 1 https://github.com/nobodyohm-web/ThotWrote 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/commands/nobodyohm-web/thot/harden)<a href="https://agentmods.dev/commands/nobodyohm-web/thot/harden"><img src="https://agentmods.dev/badge/commands/nobodyohm-web/thot/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/commands/nobodyohm-web/thot/harden"><img src="https://agentmods.dev/badge/commands/nobodyohm-web/thot/harden.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 | $0.00017 | $0.00200 |
| Opus 5.5 | $0.00007 | $0.00080 |
| Sonnet 5.5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
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 1mo 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.
What it actually says
Corrige le finding n°$1 de la dernière liste /audit.
L'ordre compte :
- Relis le code avec
read_file— pas seulement la ligne du sink, la fonction entière et ses appelants (callers). - 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.
- Corrige. Relance le test, montre-moi qu'il passe.
- 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.
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.
- 1mo ago First seen · 19 lines · 17 tokens per session scan A 714242a0bf92
harden is a command published in the GitHub repository nobodyohm-web/Thot (0 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 200 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
t00-playwright-test
A command for testing a locally running web app in a real browser with Playwright, a browser automation and testing tool. It checks normal user flows and selected edge cases, then reports results with screenshots.
gsd-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.