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.
npx skills add ViryaZheng/recomby-geo --skill geo-pipelinegit clone --depth 1 https://github.com/ViryaZheng/recomby-geoWrote 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/skills/viryazheng/recomby-geo/geo-pipeline)<a href="https://agentmods.dev/skills/viryazheng/recomby-geo/geo-pipeline"><img src="https://agentmods.dev/badge/skills/viryazheng/recomby-geo/geo-pipeline/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/skills/viryazheng/recomby-geo/geo-pipeline"><img src="https://agentmods.dev/badge/skills/viryazheng/recomby-geo/geo-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00169 | $0.01115 |
| Opus 5 | $0.00084 | $0.00558 |
| Sonnet 5 | $0.00034 | $0.00223 |
| Haiku 4.5 | $0.00017 | $0.00112 |
Grade A, and why
geo-pipeline 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.
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-pipeline — Codex orchestrator for recomby-geo
On Claude Code each stage is a bare slash command (/01-intake …
/07-reaudit). Codex CLI has no bare custom commands, so this skill is the
Codex entry point: it carries the orchestration rules and routes to the
per-stage specification files, which are the single source of truth
shared with the Claude Code side. Do not duplicate stage logic here — read
the stage file and follow it.
Per-stage specs (read the one you're running):
commands/01-intake.md, commands/02-audit.md, commands/03-gap.md,
commands/04-content-brief.md, commands/05-production.md,
commands/06-distribution.md, commands/07-reaudit.md (relative to this
plugin's root). Full directory convention + dependency graph:
orchestrator/run.md.
How to run a stage on Codex
-
Identify the client folder
clients/<slug>/and the stage the user wants. -
Read the matching
commands/0X-*.mdand execute its Procedure verbatim. -
Validate every JSON artifact the stage writes against its schema before moving on (Codex has no built-in schema validation — run it explicitly):
python3 - <<'PY' import json, jsonschema pairs = { "brand_context.json": "brand_context.schema.json", "visibility_baseline.json": "visibility_baseline.schema.json", "content_priorities.json": "content_priorities.schema.json", } # see schemas/ for the full set incl. attribution_diff + review_feedback # jsonschema.Draft202012Validator(json.load(open("plugins/recomby-geo/schemas/<file>"))).validate(json.load(open("clients/<slug>/<artifact>"))) print("validate each artifact against plugins/recomby-geo/schemas/*.schema.json") PY -
Stop at the human-in-loop points (see rules below).
Stage order (never run out of order)
inputs/ → 01-intake → brand_context.json
→ 02-audit → visibility_baseline.json
→ 03-gap → content_priorities.json
→ 04-content-brief → briefs/<id>.md (+ .html, REQUIRED-FILL slots)
[EXPERT FILLS THE SLOTS — not the AI]
04 Step 9 verifies fills → status: ready-for-production
→ 05-production → drafts/<id>.md (+ review .html)
→ 06-distribution → distribution/<id>.json + publish-bundle.md
[PUBLISH + WAIT 7+ days]
→ 07-reaudit (monthly) → reaudit/round-N.json → feeds next 03-gap
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 · 87 lines · 169 tokens per session scan A dfea623da7fd
geo-pipeline is a skill published in the GitHub repository ViryaZheng/recomby-geo (454 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 1,115 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
code-agent
General-purpose coding agent that reads, writes, and edits code, and searches codebases.
code-review
AI-powered code review for diffs and individual files using LLM analysis.
code-plan
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
code-review-github
GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge.
code-review-standards
Discover and apply organization coding standards from .forge-review/ configuration.
tavily-research
Deep multi-source research using Tavily Research API.