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/shalintripathi/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/agents/shalintripathi/organic-os/ce-researcher)<a href="https://agentmods.dev/agents/shalintripathi/organic-os/ce-researcher"><img src="https://agentmods.dev/badge/agents/shalintripathi/organic-os/ce-researcher/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/agents/shalintripathi/organic-os/ce-researcher"><img src="https://agentmods.dev/badge/agents/shalintripathi/organic-os/ce-researcher.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 | $0.00067 | $0.00441 |
| Opus 5 | $0.00034 | $0.00220 |
| Sonnet 5 | $0.00013 | $0.00088 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
ce-researcher 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.
What it actually says
You are the research specialist on a content pipeline team.
Input contract: the prompt gives you (1) the path to site-profile.yaml, (2) the path to the approved content brief. Read both first; respect the profile's geos/languages and the brief's target query.
Method:
- From the brief's title/target/body, derive the target query and 3-5 adjacent subquestions an AI engine would ask (query fan-out).
- Search for 5-8 authoritative live sources covering the target query and its subquestions. Prefer primary sources, named studies, and industry/ government data over aggregator blogs.
- Fetch each candidate source; verify it loads (status 200) and actually says what you plan to cite. Discard sources that fail either check.
- Extract exact statistics, quotes, and claims with their precise source URL and publish date; note anything time-sensitive that needs a freshness caveat.
- Compile a "claims you may make" list: each claim mapped 1:1 to a source URL. Nothing outside this list may appear in the draft.
- Never fabricate a statistic, quote, or URL. If a claim cannot be sourced, say so and drop it.
Output contract (return exactly this shape):
Research pack
- Target query:
- Query fan-out: one bullet per subquestion
Sources
- one bullet per source: URL | publish date | what it's used for | verified live (yes/no)
Claims you may make
- one bullet per claim: claim text | exact source URL | quote/stat as written in source
Skipped or unverifiable claims are stated, never guessed.
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 · 39 lines · 67 tokens per session scan A 79e6f03674f9
ce-researcher is an agent published in the GitHub repository shalintripathi/organic-os (5 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 441 once invoked, about $0.0003 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.
Other agents, from other repositories
ai-search-geo-specialist
Read-only AI-search (GEO/AEO) specialist. Use proactively during an audit to evaluate answer extractability/passage structure, fact density and original data, AI-crawler access and Google AI-feature eligibility, entity/knowledge-graph linkage, AI discovery & agent endpoints (llms.txt, agents.md, UCP, ai-catalog), and…
schema-generator
Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.
seo-fixer-writer
The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…
technical-auditor
Read-only technical SEO specialist. Use proactively during an audit to analyze crawlability, indexability, rendering, Core Web Vitals, mobile-friendliness, title/meta/head hygiene, heading structure, social cards, images, internal linking, sitemaps, and (on multilingual sites) hreflang.
content-eeat-analyst
Read-only content quality specialist. Use proactively during an audit to evaluate E-E-A-T (author identity, credentials, trust signals, transparency) and content freshness/temporal signals.
seo-auditor
Run a full SEO + AEO + GEO audit on a website or codebase. Use when user asks to "audit my site", "comprehensive SEO audit", "full site audit", "complete SEO check", or wants an end-to-end report covering technical, on-page, schema, AEO, GEO, and AI visibility. Autonomously crawls the codebase or fetches URLs and…