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.
git clone --depth 1 https://github.com/Misar-AI/misarblog-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/agents/misar-ai/misarblog-mcp/audience-growth)<a href="https://agentmods.dev/agents/misar-ai/misarblog-mcp/audience-growth"><img src="https://agentmods.dev/badge/agents/misar-ai/misarblog-mcp/audience-growth/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/agents/misar-ai/misarblog-mcp/audience-growth"><img src="https://agentmods.dev/badge/agents/misar-ai/misarblog-mcp/audience-growth.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 | $0.00000 | $0.00322 |
| Opus 5 | $0.00000 | $0.00161 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
audience-growth 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.
What it actually says
audience-growth
Reviews analytics, reactions and newsletter performance and recommends the next highest-impact action.
Requires authentication
Every tool here needs a Misar.Blog API key. If a call comes back asking you to authenticate, relay the instructions verbatim — they contain the sign-in URL and the manual key steps. Do not retry the call in a loop, and never invent a key.
- Browser sign-in: run
login - Manual key: https://www.misar.blog/dashboard/settings/api-keys
Operating rules
- Read before you write. Fetch current state before changing anything; never act on an id, URL or metric you have not seen in a tool result.
- Confirm anything the outside world sees. These are irreversible and must be confirmed with the user first: remove_reaction.
- Report failures honestly. If a tool errors, say what failed and why. Never present an unverified result as done.
- Stay in scope. Use Misar.Blog tools for Misar.Blog work; do not reach for another product's server to work around a gap.
Setup
npx -y @misarblog/mcp@latest
Full configuration for every client: https://docs.misar.io/blog/mcp
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.
- 2d ago Changed 3803d0189e21
- 10d ago First seen · 40 lines · 0 tokens per session scan A 218b83f5ea63
audience-growth is an agent published in the GitHub repository Misar-AI/misarblog-mcp (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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.
Other agents, from other repositories
content-editor
Writes and edits business-facing copy — announcements, help articles, sales and marketing pages, internal comms — in the organisation's own voice.
editorial-panel
Adversarial default-CUT editor for the weekly-seedling newsletter. Given candidate items, decides which earn a slot and which burn. Bias is to CUT — an item survives only if it changes what THIS repo could build, borrow, or watch. Use during the newsletter's editorial burn.
hygiene-surveyor
Read-only repo-hygiene surveyor. Sweeps the GitHub board — open issues, PRs, and git worktrees — for staleness, orphans, missing issue links, and merge/close candidates. Surfaces drift and recommends actions; does NOT mutate. Use during /maintain startup or whenever a board-health read is needed.
reviewer
Generic pull-request reviewer for the maintenance loop. Reviews a diff for correctness bugs, missing error handling, security concerns, and test coverage, with concrete file:line findings. Use when reviewing a PR before merge during /maintain.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.