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/harness-check)<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/harness-check"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/harness-check/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/harness-check"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/harness-check.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 | $0.00049 | $0.00540 |
| Opus 5.5 | $0.00020 | $0.00216 |
| Sonnet 5.5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
harness-check 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 21d 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
Lance le self-test du harness :
python ~/.claude/scripts/harness-selftest.py --verbose
Puis rapporte le verdict en une ligne, et uniquement si c'est NO-GO, la liste des checks rouges. Si c'est réparable, lance la réparation :
python ~/.claude/scripts/harness-selftest.py --verbose --repair
La réparation est additive uniquement : elle ré-enregistre les blocs de hooks
manquants après un backup de settings.json. Elle ne retire jamais rien.
Pourquoi cette commande existe : les hooks sont fail-open. Un script cassé,
un Python déplacé, un settings.json réécrit par un autre outil → le hook sort 0
en silence et le harness est mort sans que rien ne le dise.
Tu n'as normalement pas à la lancer : trois mécanismes réparent déjà tout
seuls — le hook SessionStart harness-guard.ps1 (à chaque session, complet une
fois par 24 h), et, si l'utilisateur les a activés avec
scripts/register-harness-guard.ps1 (opt-in), la tâche planifiée
SGRR Harness Guard Daily (9 h) et Startup\SGRR-Harness-Guard.cmd (à chaque
démarrage). Ces deux-là vivent hors de settings.json, donc ils remettent
les hooks même si ce fichier est écrasé en entier. Journal : ~/.claude/harness/guard.log.
Cette commande sert à vérifier maintenant, sur demande, ou à diagnostiquer quand le guard signale un échec qu'il n'a pas su réparer.
Ce que le test ne couvre pas, et qu'il faut dire si on te le demande : que Claude
Code transmette bien additionalContext d'un hook PreCompact au modèle. Ça ne
se vérifie qu'en déclenchant une vraie compaction. Le doublon
SessionStart:compact, lui, est documenté et couvert.
Si le test signale un run autonome oublié ou un goal actif inattendu, le mentionner : ce sont les deux états qui peuvent surprendre une session future. Ne rien désactiver sans demander à l'utilisateur.
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.
- 21d ago First seen · 45 lines · 49 tokens per session scan A 3c6d60961811
harness-check is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 540 once invoked, about $0.0002 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 2026-10-04.
Other commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
auditar-cascading
Invoca cascading-failures-auditor — audita serviço para 5 triggers de cascade (sem timeout, retry sem jitter, sem circuit breaker, sem deadline, queue unbounded) e gera CASCADING-AUDIT.md.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.