What is session-check?

A session-readiness command that checks whether the agent is in the expected project repository and whether required skills are loaded in the current session. A repository is the project folder tracked by Git.

Use it before a coding session to verify the current directory, Git project, remote address, branch, uncommitted changes, and loaded skills.

It prevents work from starting in the wrong folder or with tools that are installed but not actually active. It reports the repository, remote, branch, and working-state details.

session-check — Command for Claude Code by Ertinox7711

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.

Clone the repo

git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/session-check/github.svg)](https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/session-check)

Your own site

<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/session-check"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/session-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/session-check"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/session-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 967 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00967
Opus 5	$0.00022	$0.00483
Sonnet 5	$0.00009	$0.00193
Haiku 4.5	$0.00004	$0.00097

Measured 12d ago against content hash 574f804ba104, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

session-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 12d 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/session-check.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the SGRR AGI V2 session-check - a fast GO / NO-GO readiness verdict. The user wants certainty on two things before they trust this session:

Right place - they are in the repo / directory they think they are ("le bon rep").
Not in the void - the rig + superpowers + skills are genuinely loaded in THIS session, not just sitting installed on disk.

Run the three groups below, then print the verdict. Be terse. Read real state - never assume.

A. Location - "am I in the right repo?"

Use the shell for the current OS (PowerShell on Windows, bash on macOS/Linux):

cwd - print the current working directory.
git root - git rev-parse --show-toplevel. If it errors, this folder is not a git repo: fine for a scratchpad, a red flag if the user expected to be inside a project.
remote - git remote -v - show the origin URL so the user can confirm it really is the project they meant (not a same-named look-alike or a stale clone).
branch + state - git status -sb - current branch, ahead/behind, clean vs dirty.
void check - if there is NO git root AND cwd is a generic dump folder (home root, Downloads, Desktop, Documents) with no project marker (.git, package.json, pyproject.toml, go.mod, Cargo.toml), flag it: that is the classic "working in the void" signal - the user is probably not where they think they are.

B. Rig loaded - "is my Claude actually souped-up right now?"

Read the live config under ~/.claude (Windows: $env:USERPROFILE\.claude):

CLAUDE.md present AND carries the rig signature - grep SGRR AGI V2, or the anticipate, verify, execute philosophy line. No signature = a default Claude.
model = opus in settings.json (max intelligence on the main loop).
sub-agents = sonnet (env.CLAUDE_CODE_SUBAGENT_MODEL) - cheap grunt-work.
context hooks - settings.hooks defines UserPromptSubmit / SessionStart / PreCompact / Stop, plus the PreToolUse pitfall coach (a hook whose command names pitfall-tips).
superpowers - enabledPlugins has superpowers@claude-plugins-official set to true. Report the total count of enabled plugins too (>= 12 expected).
memory + pitfalls - the memory index present at EITHER ~/.claude/memory/MEMORY.md OR a project-scoped ~/.claude/projects/<encoded-cwd>/memory/MEMORY.md (Claude Code stores memory globally or per-project - accept either, only flag if BOTH are missing), and PITFALLS.md present.

Read the full file on GitHub · 59 lines

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.

12d ago First seen · 59 lines · 44 tokens per session scan A 574f804ba104

Subscribe to this mod's changes

session-check is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 967 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 2026-08-31.

Claude Code Productivity ai automation claude developer-tools

session-check

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

A. Location - "am I in the right repo?"

B. Rig loaded - "is my Claude actually souped-up right now?"

What this file has done since we first saw it

Other commands, from other repositories

evolve

suggest-automation

instinct-import

instinct-export

rewind-summary

handover