shotgrid-task-management

shotgrid-task-management is a skill for Claude Code, Codex from loonghao/shotgrid-mcp-server. It costs 35 tokens per session (771 once invoked), scanned A, original, MIT.

A set of instructions for safely managing tasks in ShotGrid, a system for tracking work in media production. It covers finding, creating, updating, closing, batching, and adding review notes to tasks.

In plain words
What is it for?
Use it to search for ShotGrid tasks, inspect their current status and assignment, apply confirmed updates, handle batches, and attach review feedback.
Why use it?
Changing a task affects the production team immediately, and guessed IDs, statuses, or assignees can update the wrong record. The instructions require checking the current record and confirming important changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to search for ShotGrid tasks, inspect their current status and assignment, apply confirmed updates, handle batches, and attach review feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/loonghao/shotgrid-mcp-server/shotgrid-task-management
Install

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.

Any agent
npx skills add loonghao/shotgrid-mcp-server --skill shotgrid-task-management
Clone the repo
git clone --depth 1 https://github.com/loonghao/shotgrid-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for shotgrid-task-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management/github.svg)](https://agentmods.dev/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management)
Your own site
<a href="https://agentmods.dev/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management"><img src="https://agentmods.dev/badge/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management/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.

agentmods 80×15 button for shotgrid-task-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management"><img src="https://agentmods.dev/badge/skills/loonghao/shotgrid-mcp-server/shotgrid-task-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00771
Opus 5.5 $0.00014 $0.00308
Sonnet 5 $0.00007 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 2d ago against content hash fa28124a8a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-25, from the pricing page.

Security

Grade A, and why

shotgrid-task-management 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 2d 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.

src/shotgrid_mcp_server/data/skills/shotgrid-task-management/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Managing ShotGrid tasks

Read references/status-codes.md before setting any status — the codes are studio-specific and the value you write must be one the entity type accepts.

Read before you write

  1. schema_get with entity type Task to learn the real field names and which ones are required or editable.
  2. entity_find_one (or search_entities) to read the current record. Report the current status and assignment to the user before changing anything.
  3. Confirm the status code and the assignee with the user. A task update is a production-side effect: it is visible to the team immediately and it is not something to infer from a vague request.

Tools

Goal Tool
Read one task entity_find_one
Read several tasks search_entities
Update one task entity_update
Update many tasks with one shape batch_entity_create / batch_operations
Create a task entity_create
Attach or read review feedback shotgrid_note_create / shotgrid_note_read

Procedure

  1. Resolve the target. Search by project plus content or code; do not guess an ID. If the search returns more than one record, ask which one.
  2. Build the smallest update payload. entity_update writes only the fields you pass — omitting a field leaves it alone, so there is no need to echo the whole record back.
  3. Set the status with a valid code from references/status-codes.md.
  4. Apply the change with entity_update.
  5. Re-read the task and report what changed. A successful call that changed nothing is still worth catching.
  6. When the change carries context a teammate needs, add a note with shotgrid_note_create on the task instead of only reporting in chat.

Batching

When the same update applies to many tasks, use one batch call rather than a loop of entity_update:

  • batch_operations for mixed create / update / delete requests.
  • batch_entity_create for creating several records of one type.

Batches are capped at 100 operations (MAX_BATCH_SIZE). Split larger sets, and check the per-item results — a batch returns one entry per operation, so a partial failure is normal and must be read, not assumed away.

Read the full file on GitHub · 74 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 74 lines · 35 tokens per session scan A fa28124a8a3c

Subscribe to this mod's changes

shotgrid-task-management is a skill published in the GitHub repository loonghao/shotgrid-mcp-server (65 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 771 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.