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.
/plugin marketplace add cdeust/session-optimizernpx agentmods add plugins/cdeust/session-optimizer/marketplacegit clone --depth 1 https://github.com/cdeust/session-optimizerGrade A, and why
session-optimizer-marketplace 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "session-optimizer-marketplace",
"owner": {
"name": "Clement Deust",
"email": "[email protected]"
},
"metadata": {
"description": "Session optimizer, split into three independently installable plugins: context-guard (Stop-hook context budget + memory-writer checkpoint subagent + subagent spend tracker), refine-gate (UserPromptSubmit prompt-binding gate + /refine skill), and statusline (multi-line status bar + install skill).",
"version": "2.2.1"
},
"plugins": [
{
"name": "context-guard",
"source": "./plugins/context-guard",
"description": "Context-budget guard: a Stop hook enforces a per-model checkpoint protocol — at the WARN threshold it writes a mechanical checkpoint stub and delegates persistence to a budgeted memory-writer subagent as a reflection pause, at the hard cap it forces checkpoint-then-clear. A SubagentStop tracker surfaces true session spend (main thread + subagents). Default protocol uses only vanilla Claude Code; a scoped memory layer is detected at runtime when installed.",
"version": "2.0.1",
"author": {
"name": "Clement Deust",
"email": "[email protected]"
},
"homepage": "https://github.com/cdeust/session-optimizer",
"repository": "https://github.com/cdeust/session-optimizer",
"license": "MIT",
"keywords": [
"claude-code",
"context-window",
"token-budget",
"checkpoint",
"stop-hook",
"subagent-cost",
"session-management"
],
"category": "productivity"
},
{
"name": "refine-gate",
"source": "./plugins/refine-gate",
"description": "Prompt-binding gate: a UserPromptSubmit hook + /refine skill that resolve vague prompt references (\"the X solution\", \"like before\", \"still broken\") to concrete artifacts with evidence, then select an execution strategy from a research-backed table (15 strategies verified against 2024-2026 literaWhat ships with it
1 file beside marketplace.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.
- yesterday First seen · 102 lines scan A 343e804e1b8f
session-optimizer-marketplace is a plugin published in the GitHub repository cdeust/session-optimizer (1 stars, last pushed 7d 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
handoff-revive
Save a compact handoff checkpoint and resume in a fresh session without replaying the entire transcript via --resume. Multi-language (en/ja/zh/zh-TW/ko/es/pt/de/fr/tr — 10 total), zero-token deterministic schema validation, turn-count nudge hook, and AUTO-SAVE at 90%/95% usage (synced with Claude Code's UI…
handoff-revive-marketplace
Marketplace hosting the handoff-revive plugin for cheap session resumption.
containuity-dev
Marketplace for the containuity checkpoint-workflow plugin.
containuity
Checkpoint workflow for long-running projects: at clean breakpoints, commit, save durable memories, refresh the living design doc (source-verified), and emit a post-compaction rehydrate go-block.
tidebase
Plugin marketplace listing 1 plugin: tidebase.
tidebase
Agent auth and credential brokering (the agent calls APIs without holding the keys), plus checkpoint/resume, human approval gates, subagent fanout, and per-run cost tracking for AI agent workflows, via the Tidebase skill and MCP server.