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/Ertinox7711/SGRR-AGI-V2Wrote 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/ertinox7711/sgrr-agi-v2/cmds)<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/cmds"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/cmds/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/ertinox7711/sgrr-agi-v2/cmds"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/cmds.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 | $0.00047 | $0.00697 |
| Opus 5 | $0.00023 | $0.00349 |
| Sonnet 5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
cmds 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inventaire des slash commands de cette session. Filtre : $ARGUMENTS
Depuis Claude Code 2.1.x les commandes personnalisees et les skills sont
fusionnes dans le meme menu /. Le menu n'est donc pas vide : il est noye.
Cette commande sert a retrouver ce qui existe vraiment.
Regles de nommage (verite disque, ne pas deviner)
- Commande perso = un fichier sous
C:\Users\YOU\.claude\commands\.foo.mddonne/foo·bar/foo.mddonne/bar:foo·bar/baz/foo.mddonne/bar:baz:foo. - Skill perso = un dossier sous
C:\Users\YOU\.claude\skills\<nom>\SKILL.md. Un SKILL.md sans frontmattername:+description:n'apparait pas dans le menu — c'est le mode de disparition silencieuse le plus frequent. - Commande de plugin =
<plugin>/commands/*.md, invoquee/<plugin>:<nom>, et seulement si le plugin est atruedansenabledPluginsdeC:\Users\YOU\.claude\settings.json.
Ce que tu fais
- Liste les commandes perso :
Glob C:\Users\YOU\.claude\commands\**\*.md— donne le nom d'invocation de chacune, plus sadescriptionlue dans le frontmatter. - Liste les skills perso et repere ceux sans frontmatter valide (ils sont
installes mais muets) :
Glob C:\Users\YOU\.claude\skills\**\SKILL.md - Lis
enabledPluginsdanssettings.json, puis pour chaque plugin actif listeC:\Users\YOU\.claude\plugins\marketplaces\*\plugins\<plugin>\commands\*.md. Signale separement les plugins afalse: leurs commandes existent sur le disque mais ne sont pas chargees. - Compare a la liste de skills reellement injectee dans cette session. Ce qui est sur le disque mais absent de la session = installe, non charge — dis-le explicitement, c'est l'information utile.
Piege de version
Le binaire du terminal et l'app Desktop peuvent etre a des versions
differentes : dans ce cas les deux menus / ne sont pas les memes. Verifie
avec claude --version et signale l'ecart s'il existe, plutot que de conclure
qu'une commande a disparu.
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.
- 2d ago First seen · 50 lines · 47 tokens per session scan A 4834b419d64c
cmds is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 697 once invoked, about $0.0002 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 2026-09-09.
Other commands, from other repositories
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
evolve
Cluster related instincts into skills, commands, or agents.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
handover
Generate comprehensive context transfer document for agent session handoffs.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.