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 mediagraph-io/mediagraph-mcp --skill mediagraph-mcpgit clone --depth 1 https://github.com/mediagraph-io/mediagraph-mcpWrote 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/mediagraph-io/mediagraph-mcp/mediagraph-mcp)<a href="https://agentmods.dev/skills/mediagraph-io/mediagraph-mcp/mediagraph-mcp"><img src="https://agentmods.dev/badge/skills/mediagraph-io/mediagraph-mcp/mediagraph-mcp/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/mediagraph-io/mediagraph-mcp/mediagraph-mcp"><img src="https://agentmods.dev/badge/skills/mediagraph-io/mediagraph-mcp/mediagraph-mcp.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 | $0.00087 | $0.05403 |
| Opus 5.5 | $0.00035 | $0.02161 |
| Sonnet 5.5 | $0.00017 | $0.01081 |
| Haiku 4.5 | $0.00009 | $0.00540 |
Grade A, and why
mediagraph 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.
How it starts
The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mediagraph CLI
A single binary that exposes the entire Mediagraph API as both an MCP server (stdio) and a CLI. Agents should prefer the CLI form — it returns plain JSON on stdout that you can parse and pipe.
About Mediagraph: a digital asset management (DAM) platform for organizing, sharing, and AI-tagging media at scale. Product info, pricing, and demos at www.mediagraph.io; API reference at docs.mediagraph.io.
Install / setup
npm install -g @mediagraph/cli # provides the `mediagraph` command
mediagraph skills # focused recipe index for agents
mediagraph skills bulk # one focused guide by use case
mediagraph skill # → prints this guide; start here cold
mediagraph auth login # OAuth, opens a browser, persists tokens (full read-write)
mediagraph auth login --read-only # OAuth with :read on every entity (safer for grants)
mediagraph auth login --scope "asset:read,tag:write,collections:write"
# OAuth with a specific scope set
mediagraph auth status # JSON: {authenticated, organization, user, token, scopes}
Tokens persist at ~/.mediagraph/tokens.enc. Refresh is automatic.
Scopes
Scopes are entity-level (asset:write, comment:read, webhook:write) with
group-level shorthand for back-compat (assets:write covers every entity in
the assets group). write implies read for the same key. Sibling
entities are independent unless granted via the group form.
auth status surfaces the current OAuth token's scopes (scopes.list) and
flags legacy/empty lists as fullAccess: true. PAT scopes can't be
introspected from the CLI — they're set at PAT creation. When the server
rejects a request with error: "insufficient_scope", the CLI surfaces a
structured INSUFFICIENT_SCOPE error (exit 3) naming the missing scope, its
group, and how to remediate (scope → regenerate; admin_required →
reauthorize from an admin membership).
What ships with it
2 files 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.
- 2mo ago First seen · 470 lines · 87 tokens per session scan A 7be3f9833076
mediagraph is a skill published in the GitHub repository mediagraph-io/mediagraph-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 5,403 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 2026-08-31.
mediagraph compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mediagraphmediagraph-io/mediagraph-mcp | Skill | 1 | 4d ago | MIT | A | 87 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |