Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Session context monitoring — pressure tracking, token estimation, threshold warnings
npx claudepluginhub mistakeknot/interagency-marketplace --plugin interpulseSession context monitoring for Claude Code.
interpulse tracks how much of Claude Code's context window you've consumed during a session. Every tool call adds to a pressure score (heavier calls like Read, Grep, Task, WebFetch count more), pressure decays over idle time, and the plugin warns you as you approach the limit — Yellow at 60%, Orange at 75%, Red at 85%.
At Red, it auto-checkpoints context by writing a session summary, so you can recover gracefully instead of hitting a hard wall.
The pressure model is deliberately conservative: it's better to warn early and be wrong than to warn late and lose context.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interpulse
Check session pressure:
/interpulse:status
Or ask naturally:
"how much context have I used?"
"am I close to the limit?"
Warnings appear automatically as hooks fire — no manual checking needed for the alert thresholds.
| Signal | Weight |
|---|---|
| Standard tool call | +1.0 |
| Heavy tool call (Read, Grep, Task, WebFetch, WebSearch) | +1.5 |
| Idle decay | -0.5 per 10 minutes |
| Token estimate | Cumulative tool output length / 4 |
| Threshold | Score | Tokens |
|---|---|---|
| Green | < 60 | < 150k |
| Yellow | 60+ | 150k+ |
| Orange | 90+ | 180k+ |
| Red | 120+ | 200k+ |
hooks/
hooks.json PostToolUse hook registration
context-monitor.sh Pressure tracker — scores, warns, checkpoints
lib/
interpulse-lib.sh Shared functions
skills/
status/SKILL.md Pressure dashboard skill
Session state lives at /tmp/interpulse-${SESSION_ID}.json — ephemeral by design, since pressure resets each session.
interpulse was extracted from intercheck, which now focuses exclusively on code quality (syntax validation + auto-formatting). The context monitoring concern is orthogonal to code quality, so they're better as separate installs.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Real-time session dashboard for Claude Code — cost tracking, analytics, and smart alerts
Claudikins Automatic Context Manager - seamless context handoff for Claude Code
Live API usage in Claude Code statusline - colored progress bars, Git info, tokens, session metrics, device tracking, and more
Claude Code statusline showing info at a glance: tokens, context, model, subagents, burn rate, skills, plugins, OpenSpec specs, task lists, and more
Governor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.
A comprehensive statusline dashboard for Claude Code — session summary, quota bars, agent tracker, MCP health, message history, and more. All at a glance, no slash commands needed.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim