Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add shalintripathi/organic-os/plugin install organic-osWrote 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/shalintripathi/organic-os/start)<a href="https://agentmods.dev/skills/shalintripathi/organic-os/start"><img src="https://agentmods.dev/badge/skills/shalintripathi/organic-os/start/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/shalintripathi/organic-os/start"><img src="https://agentmods.dev/badge/skills/shalintripathi/organic-os/start.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 | $0.00083 | $0.01376 |
| Opus 5.5 | $0.00033 | $0.00550 |
| Sonnet 5.5 | $0.00017 | $0.00275 |
| Haiku 4.5 | $0.00008 | $0.00138 |
Grade A, and why
start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
organic-os start (guided front door)
This is the first thing a new or returning user should run. It never writes
anything itself - it health-checks, then hands off to setup or to whatever
the user picks from the menu.
Step 1: greet
One sentence, no hype: organic-os observes a site's search and AI-answer- engine performance, proposes changes, and only ships them once a human approves - the loop is the product.
Step 2: health check
Run each check in order and report plainly what passed and what did not. Do not stop at the first failure - collect all three results, then act.
python3on PATH:python3 --version. If missing, tell the user organic-os needs Python 3.9+ and stop here - nothing else in this skill works without it.- PyYAML importable:
python3 -c "import yaml". If this fails, show the fix and stop:python3 -m pip install --user pyyaml. Offer to run it for them. - Registry readable:
PYTHONPATH="$CLAUDE_PLUGIN_ROOT/lib" python3 -c "from core import registry; print(registry.load())". A clean{'active': None, 'sites': {}}or a populated registry both count as a pass - this check is aboutcore.registryimporting and running, not about whether any site exists yet.
If all three pass, say so in one line and move to Step 3.
Step 3: route
Use the Step 2 registry read to decide which branch applies.
Registry empty (no sites)
Offer two paths, AskUserQuestion with options:
- Quick start - URL, then 2 more questions, sensible defaults, about 2 minutes.
- Full setup - audits the URL first (brand voice, audience, keywords, competitors, geos proposed from the actual site, not asked blind), then covers whatever the audit cannot infer: operator knowledge, connectors, Google Ads, WordPress, approval channel, runtime, brain location and mode.
Mention the install form once, before handing off: if you filled the configuration form when you enabled the plugin, setup will use it - nothing is asked twice, and a filled form makes quick start a single confirmation click.
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 · 123 lines · 83 tokens per session scan A db847b08ac12
start is a skill published in the GitHub repository shalintripathi/organic-os (5 stars, last pushed 19d ago), licensed MIT. It adds 83 tokens to every session and 1,376 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
import-sop
Import agency procedures as role-assigned SOP steps with approval gates. "import our launch checklist".
client-onboarding
Build a client onboarding pack: kickoff agenda, discovery questions, 30-60-90. "we just signed a new client".
webinar-plan
Plan a webinar end to end: run of show, registration copy, promotion, follow-up. "plan a webinar on X".
optimize-page
Comprehensive single-page optimization across all three layers — traditional SEO (title / meta / H1 / internal links), AEO (chunk quality, direct-answer leads, FAQ extraction), and GEO rewrites using the tactics published by the Princeton/IIT Delhi GEO study (citation integration, expert quotes, statistics enrichment…
seo-audit
Single audit entry point — surface-level scorecard or deep infrastructure dive depending on the requested mode. Default full mode produces a multi-layer scorecard across all 9 areas (crawlability, indexation, meta tags, headings, images, Core Web Vitals, JS rendering, mobile + security, structured data, internal…