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 loonghao/shotgrid-mcp-server --skill shotgrid-entity-searchgit clone --depth 1 https://github.com/loonghao/shotgrid-mcp-serverWrote 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/loonghao/shotgrid-mcp-server/shotgrid-entity-search)<a href="https://agentmods.dev/skills/loonghao/shotgrid-mcp-server/shotgrid-entity-search"><img src="https://agentmods.dev/badge/skills/loonghao/shotgrid-mcp-server/shotgrid-entity-search/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/loonghao/shotgrid-mcp-server/shotgrid-entity-search"><img src="https://agentmods.dev/badge/skills/loonghao/shotgrid-mcp-server/shotgrid-entity-search.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 | $0.00035 | $0.00800 |
| Opus 5.5 | $0.00014 | $0.00320 |
| Sonnet 5.5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
shotgrid-entity-search 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searching ShotGrid entities
Read references/filters.md before writing any non-trivial filter — it lists
every operator the server accepts and the time-filter shapes that are easy to
get wrong.
Pick the tool first
| Goal | Tool |
|---|---|
| Several entities of one type, with filters and field selection | search_entities |
| One type plus fields from linked entities (shots with their sequence names) | search_entities_with_related |
| Exactly one entity, by ID or a unique field | entity_find_one |
| Complex boolean logic, grouping, or aggregate summaries | sg_search_advanced |
| Full-text search across entity types | sg_text_search |
| Which fields exist on a type? | schema_get or sg_schema_field_read |
| Which entity types exist? | sg_schema_entity_read |
search_entities_with_related and sg_search_advanced cost one round trip
where several search_entities calls would cost many. Use them when the answer
needs linked data; stay with search_entities for a flat list.
Procedure
- Confirm the entity type. ShotGrid type names are capitalised and often
studio-specific (
Shot,Asset,Task,Version,PublishedFile,CustomEntity01). If the type is uncertain, callsg_schema_entity_readonce rather than guessing. - Confirm the fields. Call
schema_getfor the entity type when you are about to filter or return a field you have not seen. A misspelled field name fails the whole query. - Always bound the query. Add a
projectfilter, a status filter, or a date filter before requesting results. An unboundedsearch_entitieson a live production can return tens of thousands of rows. - Request only the fields you need in
fields. Entity records are wide; the default field set is a convenience, not a budget. - Filter in ShotGrid, not in the model. Push every condition into
filters. Never fetch a broad result set and narrow it by reading.
Example
Find in-progress shots of a project, newest update first:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 75 lines · 35 tokens per session scan A a98b8441524d
shotgrid-entity-search is a skill published in the GitHub repository loonghao/shotgrid-mcp-server (67 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 800 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 2026-09-23.
shotgrid-entity-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shotgrid-entity-searchloonghao/shotgrid-mcp-server | Skill | 67 | 3d ago | MIT | A | 35 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |