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/mishahanin/heading-os-marketplaceWrote 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/plugins/mishahanin/heading-os-marketplace/heading-core)<a href="https://agentmods.dev/plugins/mishahanin/heading-os-marketplace/heading-core"><img src="https://agentmods.dev/badge/plugins/mishahanin/heading-os-marketplace/heading-core/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/plugins/mishahanin/heading-os-marketplace/heading-core"><img src="https://agentmods.dev/badge/plugins/mishahanin/heading-os-marketplace/heading-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
heading-core 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.
What it actually says
{
"name": "heading-core",
"description": "Sovereignty and session core: the prime/state-check/checkpoint skills, the standalone sovereignty guard hooks, and the session checkpoint system - a context-usage sensor, a threshold offer, a pre-compaction brief that states what the summary must keep verbatim, a redacted post-compact save, and a resume injector, all keyed by session so concurrent sessions never overwrite each other. Two optional switches: a hands-off auto mode that saves without asking, and an unattended mode that waits out a grace period at a pause and carries on when nobody answers, bounded by a no-progress fuse and a continuation ceiling.",
"author": {
"name": "Misha Hanin",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 3 skills, 2 commands travel with it, and installing the plugin installs all of them — 276 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 9 lines scan A b1ef3f9a2088
heading-core is a plugin published in the GitHub repository mishahanin/heading-os-marketplace (2 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
handoff
Manual /handoff skill — writes a structured resume doc on demand, auto-loads it on next session.
engram
Filesystem-backed agent memory for Claude Code.
wire-plugins marketplace
Official Claude Code plugins from Wire — persistent memory, context management, and AI agent tools.
recall
Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved context.
memory-loop
A memory lifecycle for Claude Code's native file-based memory: a save gate against hallucinated memories, tiered expiry (short-tier memories archived — never deleted — when they lapse), a propose-then-confirm consolidation pass (merge/dedupe long-tier memory), a correction-signal hook that logs likely corrections for…
continuity
Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.