A command that performs one limited work cycle for an eGEOagents workspace, a system for collecting and analysing information about a domain. It reads the current project state, completes one task, saves the results, and closes the run.

Use it to process fresh collector data, create signal or document files, update existing findings, and record a completed run for one domain.

It keeps automated research work bounded and traceable instead of allowing an open-ended process to change the workspace indefinitely.

geo:loop — Command for Claude Code by mverab/eGEOagents

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/mverab/eGEOagents

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/mverab/egeoagents/geo-loop/github.svg)](https://agentmods.dev/commands/mverab/egeoagents/geo-loop)

Your own site

<a href="https://agentmods.dev/commands/mverab/egeoagents/geo-loop"><img src="https://agentmods.dev/badge/commands/mverab/egeoagents/geo-loop/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/mverab/egeoagents/geo-loop"><img src="https://agentmods.dev/badge/commands/mverab/egeoagents/geo-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 809 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	$0.00035	$0.00809
Opus 5.5	$0.00014	$0.00324
Sonnet 5.5	$0.00007	$0.00162
Haiku 4.5	$0.00003	$0.00081

Measured 1mo ago against content hash 6cc1ed5afaac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

geo:loop 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.

.claude/commands/geo-loop.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/geo:loop Command

Execute one eGEOagents loop iteration. Loop state lives in the workspace resolved from $EGEO_HOME (default ~/.egeo/); the repo tree is never written to. One-shot /geo <url> is unaffected.

Follow .claude/skills/geo-loop/SKILL.md — it is the authoritative procedure.

Workflow

Resolve the domain - Use $ARGUMENTS.domain. If omitted and exactly one directory exists under $EGEO_HOME/domains/ (excluding egeo-core), use it; otherwise list the domains and stop.
Plan - egeo loop run <domain> --dry-run. Writes nothing. Non-zero exit means stop and report (egeo loop doctor explains why).
Read state - domain charter, data/*.jsonl deltas, existing signals/, docs/, config.yaml.
One unit of work - from ## Current focus, else the first Backlog item. Reuse content-scoring, competitive-analysis, schema-generator. No fresh data and nothing actionable = Outcome: no-op.
Write artifacts - signals/<slug>.md / docs/<slug>.md per SUBSTRATE.md. Re-observed evidence increments frequency on the existing signal instead of creating a file.
Close the run - append exactly one ### YYYY-MM-DD run Timeline entry ending in Outcome: success|partial|failure|no-op, and exactly one LOG.md line. Update ## Current focus if it was completed.
Verify - python -m egeo.substrate_lint and egeo loop doctor, then re-read both appends. Violations are fixed before exiting.

Execution

Loop run: $ARGUMENTS.domain

Step 1/6: Plan
→ egeo loop run $ARGUMENTS.domain --dry-run

Step 2/6: Reading workspace state
→ $EGEO_HOME/domains/$ARGUMENTS.domain/README.md, data/, signals/, docs/

Step 3/6: Unit of work
→ <focus item>

Step 4/6: Writing artifacts
→ signals/... / docs/...

Step 5/6: Closing the run
→ Timeline entry + LOG.md line

Step 6/6: Verification
→ substrate_lint + doctor + re-read

Output

Written to $EGEO_HOME/ (never geo-output/):

signals/[slug].md - evidence, deduped and frequency-counted
docs/[slug].md - durable knowledge, citing signals and sources
domains/[domain]/README.md - one appended Timeline entry
LOG.md - one appended line

Read the full file on GitHub · 87 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.

1mo ago First seen · 87 lines · 35 tokens per session scan A 6cc1ed5afaac

Subscribe to this mod's changes

geo:loop is a command published in the GitHub repository mverab/eGEOagents (207 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 809 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 2026-08-30.

Research aeo ai-search-optimization content-optimization generative-engine-optimization geo schema-markup

seo-geo

SEO/GEO end-to-end along the SITE loop: survey demand and competitors, implement content, tune quality/tech/on-page, and evaluate authority/rankings/reports/memory (--phase survey|implement|tune|evaluate). Not sure? Use /aaron-marketing:auto.

aaron-he-zhu/aaron-marketing-skills · 58 tokens

launch

Run a product-launch (RAMP) workflow: positioning and launch tiering, window/early-access design, message house and asset kits, the launch-readiness gate with a T-1 go/no-go, launch-day execution, and the post-launch prove loop. Not sure? Use /aaron-marketing:auto.

aaron-he-zhu/aaron-marketing-skills · 64 tokens

narrative

Run a brand-narrative & messaging (TALE) workflow: trace the current message and positioning truth, architect the durable message house/voice/story canon, land it consistently across every surface, and evaluate resonance with tests and drift monitoring. Not sure? Use /aaron-marketing:auto.

aaron-he-zhu/aaron-marketing-skills · 59 tokens

social

Run an organic-social (ECHO) workflow: channel portfolio and voice dossiers, platform-native content and calendars, the social-quality gate with a pre-publish go/no-go, community/inbox/crisis operations, and the listening/SOV/dark-social measurement loop. Not sure? Use /aaron-marketing:auto.