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 PostLake/postlake-mcp --skill postlake-mediagit clone --depth 1 https://github.com/PostLake/postlake-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/postlake/postlake-mcp/postlake-media)<a href="https://agentmods.dev/skills/postlake/postlake-mcp/postlake-media"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-media/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/postlake/postlake-mcp/postlake-media"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-media.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 | $0.00043 | $0.00784 |
| Opus 5.5 | $0.00017 | $0.00314 |
| Sonnet 5.5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
postlake-media scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.postlake.dev/v1/media \ How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PostLake: upload media
Upload the file first to get a med_… id, then pass it as media in a publish or
schedule call. Some platforms require media (Instagram, TikTok, YouTube, Pinterest).
Auth
Authorization: Bearer $POSTLAKE_API_KEY
Base URL https://api.postlake.dev.
Upload
POST the raw bytes with the file's Content-Type. Limits: images ≤20MB
(jpeg/png/webp/gif); videos ≤200MB (mp4/mov/webm).
From a local file:
curl -X POST https://api.postlake.dev/v1/media \
-H "Authorization: Bearer $POSTLAKE_API_KEY" \
-H "Content-Type: image/jpeg" \
--data-binary @photo.jpg
From a URL (download it first, then upload the bytes):
curl -sL "https://example.com/photo.jpg" -o /tmp/m.jpg
curl -X POST https://api.postlake.dev/v1/media \
-H "Authorization: Bearer $POSTLAKE_API_KEY" \
-H "Content-Type: image/jpeg" \
--data-binary @/tmp/m.jpg
Response:
{ "id": "med_47214a…", "url": "https://media.postlake.dev/med_47214a…", "contentType": "image/jpeg", "size": 86487 }
Attach it to a post
Pass the id(s) as media, with optional alt text for accessibility:
curl -X POST https://api.postlake.dev/v1/posts \
-H "Authorization: Bearer $POSTLAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"text": "New drop 👟",
"accounts": ["acc_54d8…"],
"media": ["med_47214a…"],
"mediaAlt": ["A pair of orange running shoes"]
}'
Tips
- For removal, distinguish the social post from its uploaded file. Cancelling or retracting a post keeps its uploads and does not refund spent publishing credits.
- List stored files with
GET /v1/media. Preview irreversible erasure withGET /v1/media/{id}/deletion; only after owner confirmation send its snapshot toDELETE /v1/media/{id}. Drafts and pending publication block erasure. - MCP provides the same flow through
manage_media: list, preview_delete, then delete with the confirmed snapshot. Erasure leaves social copies online but removes PostLake previews. Storage failures remain retryable. - Uploads retain a minimum of 90 days while the account remains open, extended for scheduled references through terminal outcome plus 30 days if later. There is no automatic expiry. Explicit erasure and legal/security removal are exceptions. Sources are public URLs, not confidential storage. Keep originals. See https://docs.postlake.dev/media#deletion.
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 Changed · +14 lines 5c54062221e9
- 2mo ago Changed 44126db868c3
- 2mo ago First seen · 73 lines · 43 tokens per session scan A 924143df12db
postlake-media is a skill published in the GitHub repository PostLake/postlake-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 784 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
postlake-media compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| postlake-mediaPostLake/postlake-mcp | Skill | 3 | 1mo ago | MIT | A | 43 | Claude Code |
| api-integration-architectsickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 33 | Claude Code |
| jellyfinmudler/LocalAI | Skill | 50k | today | MIT | A | 70 | Claude Code, Codex |
| mirrord-prev-envmetalbear-co/mirrord | Skill | 5.4k | today | MIT | A | 122 | Claude Code, Codex |
| horse-integration-testsHashLoad/horse | Skill | 1.4k | 8d ago | MIT | A | 25 | Claude Code, Codex |
| smoke-testSkyvern-AI/skyvern | Skill | 23k | today | AGPL-3.0 | A | 50 | Claude Code, Codex |
| makeericrisco/rsc-harness | Skill | 529 | 3d ago | MIT | A | 127 | Claude Code, Codex |