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-accountsgit 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-accounts)<a href="https://agentmods.dev/skills/postlake/postlake-mcp/postlake-accounts"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-accounts/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-accounts"><img src="https://agentmods.dev/badge/skills/postlake/postlake-mcp/postlake-accounts.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 | $0.00056 | $0.00575 |
| Opus 5.5 | $0.00022 | $0.00230 |
| Sonnet 5.5 | $0.00011 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
postlake-accounts 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 https://api.postlake.dev/v1/social-accounts \ What it actually says
PostLake: connected accounts
Returns each connected account's acc_… id, platform, handle, and health
status. You only need this if you want to post to specific accounts by id. For most posts it's simpler to skip the lookup and post to a whole profile by
name (see the postlake-publish skill). Handy here for checking which accounts
are connected and whether any show status: "needs_reauth" (they need
reconnecting before they can post).
Auth
All requests use a Bearer key from the POSTLAKE_API_KEY environment variable:
Authorization: Bearer $POSTLAKE_API_KEY
Get a key at https://app.postlake.dev/app/keys. Base URL: https://api.postlake.dev.
List connected accounts
curl https://api.postlake.dev/v1/social-accounts \
-H "Authorization: Bearer $POSTLAKE_API_KEY"
Response:
{
"accounts": [
{ "id": "acc_84a4…", "platform": "bluesky", "handle": "yourbrand.bsky.social", "status": "active" },
{ "id": "acc_e553…", "platform": "linkedin", "handle": "Your Name", "status": "active" },
{ "id": "acc_54d8…", "platform": "instagram","handle": "yourbrand", "status": "needs_reauth" }
]
}
status: "active": ready to post.status: "needs_reauth": the connection expired; the user must reconnect it at https://app.postlake.dev/app/channels before posting to that account.
Connecting new accounts
Connecting a platform is an OAuth flow a human completes in the browser. If a platform the user wants isn't listed, tell them to connect it at https://app.postlake.dev/app/channels, then re-list.
What platforms support
To check limits/options for a platform (character limits, media rules) before composing, call the public capabilities endpoint (no auth needed):
curl https://api.postlake.dev/v1/platforms/bluesky
Tips
- Always resolve account ids from here rather than guessing.
- Skip accounts with
status: "needs_reauth"and tell the user to reconnect.
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 · -1 lines f3124054569c
- 2mo ago First seen · 67 lines · 56 tokens per session scan A 4aa1601cdd2f
postlake-accounts is a skill published in the GitHub repository PostLake/postlake-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 575 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-accounts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| postlake-accountsPostLake/postlake-mcp | Skill | 3 | 1mo ago | MIT | A | 56 | 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 |