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/gowtham012/Claude-pluginsWrote 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/gowtham012/claude-plugins/carry-forward)<a href="https://agentmods.dev/plugins/gowtham012/claude-plugins/carry-forward"><img src="https://agentmods.dev/badge/plugins/gowtham012/claude-plugins/carry-forward/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/gowtham012/claude-plugins/carry-forward"><img src="https://agentmods.dev/badge/plugins/gowtham012/claude-plugins/carry-forward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
carry-forward 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 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.
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": "carry-forward",
"description": "Persists Claude Code session context across sessions. Auto-saves after every response. Auto-loads at session start via CLAUDE.md import.",
"version": "1.0.0",
"author": { "name": "Gowtham" },
"license": "MIT",
"homepage": "https://github.com/gowtham012/Claude-plugins/tree/main/carry-forward",
"repository": "https://github.com/gowtham012/Claude-plugins",
"keywords": ["memory", "context", "session", "persistence"]
}
What it installs
The manifest is a name and a version. 4 skills, 1 hook travel with it, and installing the plugin installs all of them — 147 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 11 lines scan A 5ff4d5d34e87
carry-forward is a plugin published in the GitHub repository gowtham012/Claude-plugins (5 stars, last pushed 7mo ago), licensed MIT. 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
memory-lens
Recalls the few memories related to each prompt: one line for the human, one context entry for the model. Local files only, no network on the hot path.
basic-memory
The bridge between Claude's working memory and Basic Memory's durable knowledge graph — session briefings, pre-compaction checkpoints, and capture reflexes.
memory-toolkit
Session memory lifecycle for developers — structured markdown memory, workstreams, handoff, auto-save hooks. No vector DB, no external dependencies.
magician
Skills and agents for the software lifecycle in Claude Code: research, design, planning, test-first building, code review, security checks and release. Includes a local code index, per-project workspace notes, stack-specific guidance at session start, and optional Jira and Confluence access.
mnemo-mcp
Persistent AI memory — store, search, and recall knowledge across sessions.
odin
Turn scattered information into a durable, provenance-tracked knowledge base. Bundles the Odin skill (judgment) and the neutral Core MCP server (deterministic, invariant-guaranteeing ops). AI is the enabler, not the substrate — the knowledge persists as Markdown + links + git with no vendor lock-in (ADR-0008).