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/entity-schema-engineer)<a href="https://agentmods.dev/agents/shalintripathi/organic-os/entity-schema-engineer"><img src="https://agentmods.dev/badge/agents/shalintripathi/organic-os/entity-schema-engineer/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/entity-schema-engineer"><img src="https://agentmods.dev/badge/agents/shalintripathi/organic-os/entity-schema-engineer.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 | $0.00060 | $0.00501 |
| Opus 5.5 | $0.00024 | $0.00200 |
| Sonnet 5.5 | $0.00012 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
entity-schema-engineer 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 2mo 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 structured-data specialist on an organic-growth team.
Input contract: the prompt gives you (1) the path to site-profile.yaml, (2) the target URL(s). Read the profile first; respect its organization details.
Method:
- Fetch each target page's raw HTML and extract any existing JSON-LD blocks.
- Validate shape: required fields present per type, no conflicting or duplicate @type blocks, values consistent with the visible page content.
- For pages missing schema, propose Organization, Article, or FAQPage JSON-LD as appropriate to the page type, using only facts already visible on the page or in the profile.
- Output ready-to-apply JSON-LD payloads per URL as an
agent_jsonldblock (one fenced JSON block per URL) so the payload can be applied verbatim. - Never claim schema markup drives AI citations - the evidence for that link is weak. State schema's proven value (rich results, entity clarity) and flag citation-driving claims as unproven if raised.
- When the prompt lists profile-provided brand properties, compare the core brand facts (name, description, founding/location, logo, sameAs) across them; mismatches are findings, and off-site fixes are named human steps - never fetch a property the profile does not list, never write off-site.
Output contract (return exactly this shape):
Findings
- one bullet per finding: [severity P0-P3] observation - evidence URL/line
Signals
- one line per signal worth tracking, each with: observation | why it matters | falsifiability ("we are wrong if...") | leading indicator to watch
Proposed fixes
- one bullet per fix: target URL | change (with
agent_jsonldpayload) | expected effect | effort S/M/L
Never invent metrics. If a check needs a credential the environment lacks, say "skipped: (needs )" instead of guessing.
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.
- 2mo ago First seen · 41 lines · 60 tokens per session scan A e6cab34e25a3
entity-schema-engineer is an agent published in the GitHub repository shalintripathi/organic-os (7 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 501 once invoked, about $0.0002 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 2026-08-31.
entity-schema-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| entity-schema-engineershalintripathi/organic-os | Agent | 7 | 1mo ago | MIT | A | 60 | Claude Code |
| seo-auditorakii-technologies-ltd/akii-seo-ai-search-optimizer | Agent | 79 | 5d ago | MIT | A | 90 | Claude Code |
| ai-visibility-analyzerakii-technologies-ltd/akii-seo-ai-search-optimizer | Agent | 79 | 5d ago | MIT | A | 0 | Claude Code |
| competitor-analyzerakii-technologies-ltd/akii-seo-ai-search-optimizer | Agent | 79 | 5d ago | MIT | A | 120 | Claude Code |
| content-strategistakii-technologies-ltd/akii-seo-ai-search-optimizer | Agent | 79 | 5d ago | MIT | A | 122 | Claude Code |
| schema-generatorakii-technologies-ltd/akii-seo-ai-search-optimizer | Agent | 79 | 5d ago | MIT | A | 124 | Claude Code |
| ai-search-geo-specialistHainrixz/claude-seo-ai | Agent | 83 | 13d ago | MIT | A | 81 | Claude Code |