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-publishgit 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-publish)<a href="https://agentmods.dev/skills/postlake/postlake-mcp/postlake-publish"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-publish/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-publish"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-publish.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 | $0.00054 | $0.00842 |
| Opus 5.5 | $0.00022 | $0.00337 |
| Sonnet 5.5 | $0.00011 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
postlake-publish 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 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.
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/posts \ How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PostLake: publish a post now
Publishes one caption to as many connected accounts as you like, in one call.
Each platform is attempted independently and the response reports per-platform
state and url.
Auth
Authorization: Bearer $POSTLAKE_API_KEY
Base URL https://api.postlake.dev.
Choosing where to post
Two ways to say which accounts a post goes to: pick whichever is simpler:
- By profile (simplest): a profile is a named group of connected accounts
(a brand, a client, "me"). Pass
"profile": "my-brand"and it posts to every account in it. Add"platforms": ["bluesky","linkedin"]to narrow it to certain networks. No id lookup needed. - By account id (precise): pass
"accounts": ["acc_…"]for exact accounts. Get the ids from thepostlake-accountsskill (GET /v1/social-accounts).
Provide profile, accounts, or both. At least one is required.
Publish
# Simplest: post to a whole profile.
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": "Shipping something new today 🚀",
"profile": "my-brand"
}'
To hit specific networks in that profile add "platforms": ["bluesky"]; to
target exact accounts use "accounts": ["acc_84a4…","acc_e553…"] instead.
Response (normalised: reason over targets):
{
"id": "post_…",
"state": "published",
"targets": [
{ "platform": "bluesky", "state": "published", "url": "https://bsky.app/profile/…/post/…" },
{ "platform": "linkedin", "state": "published", "url": "https://www.linkedin.com/feed/update/…" }
]
}
state per target is one of published, processing (async platforms like
TikTok/YouTube: poll GET /v1/posts/{id} until final), failed (see
target.error), or scheduled.
Options
- Attach media: upload first with the
postlake-mediaskill, then pass the ids:"media": ["med_…"](with optional"mediaAlt": ["alt text"]). - Per-platform captions:
"textOverrides": { "x": "shorter for X", "linkedin": "…" }. - Platform-specific settings:
"platformOptions": { "pinterest": { "boardId": "…" }, "youtube": { "title": "…", "privacyStatus": "private" } }.
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 Changed 043c8e9a04d0
- 2mo ago First seen · 84 lines · 54 tokens per session scan A 5b1b06caeebf
postlake-publish is a skill published in the GitHub repository PostLake/postlake-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 842 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-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| postlake-publishPostLake/postlake-mcp | Skill | 3 | 1mo ago | MIT | A | 54 | 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 |