claude

interspect

Agent and skill performance profiler and routing optimizer. Collects evidence about flux-drive agent accuracy and skill quality, proposes routing overrides and skill overlays for underperformers, and monitors canary periods. Companion plugin for Clavain.

0 on GitHubby mistakeknotv0.1.27MITupdated 8 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin interspect in mistakeknot/interspect. Commands read from the repo's manifest — 7 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (18)

  • /interspect:calibrate-audit

    Self-audit interspect calibration — compare current ranking vs a snapshot from N days ago, flag drift

  • /interspect:calibrate

    Compute agent scores and delegation stats from evidence, write routing + delegation calibration

  • /interspect:delegation-status

    Show delegation routing status — pass rates, recent outcomes, calibration state

  • /interspect:interspect-approve

    Promote pending proposals to active routing overrides

  • /interspect:interspect-correction

    Record that an agent got something wrong — high-quality manual evidence for Interspect

  • /interspect:interspect-disable-autonomy

    Disable autonomous mode — all overrides require explicit approval

  • /interspect:interspect-effectiveness

    Show routing effectiveness metrics — override rate trends, per-agent impact, and actionable recommendations

  • /interspect:interspect-enable-autonomy

    Enable autonomous mode — low/medium-risk overrides auto-apply with canary monitoring

  • /interspect:interspect-evidence

    Detailed evidence view for a specific agent — event breakdown, timeline, recent events

  • /interspect:interspect-health

    Signal collection diagnostics — check evidence channels, dark sessions, DB health

  • /interspect:interspect-override

    Manually exclude an agent from flux-drive triage — bypasses evidence requirements

  • /interspect:interspect-propose

    Detect routing-eligible patterns and propose agent exclusions

  • /interspect:interspect-reset

    Nuclear reset — revert all active modifications, clear evidence, archive data

  • /interspect:interspect-revert

    Revert a routing override (agent), an agent overlay, or a tool remediation

  • /interspect:interspect-status

    Interspect overview — session counts, evidence stats, active canaries, and modifications

  • /interspect:interspect-tune

    Generate a prompt tuning overlay for an agent, a CLAUDE.md remediation for a tool source, or a skill overlay for a skill, from accumulated evidence

  • /interspect:interspect-unblock

    Remove a pattern from the routing override blacklist

  • /interspect:interspect

    Analyze Interspect evidence — detect patterns, classify by counting-rule thresholds, report readiness

Hooks (3)

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/interspect-session.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/interspect-evidence.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/interspect-session-end.sh

View source on GitHub

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Tenant-isolated AI teams that plan work, coordinate tasks, recall approved context, and return evidence-backed results

6 skills · 6 commands · 4 agents · 1 MCP server

ruvnet/ruflo 81,589

data

claude

Data engineering for Apache Airflow and Astronomer. Author DAGs with best practices, debug pipeline failures, trace data lineage, profile tables, migrate Airflow 2 to 3, and manage local and cloud deployments.

35 skills · hooks

anthropics/claude-plugins-official 47,076

protect-mcp

claudecodex

Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.

1 skill · 2 commands · 2 agents · hooks

wshobson/agents 42,461

Maven Bio

claude

Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.

16 skills · 1 agent · 1 MCP server

anthropics/knowledge-work-plugins 35,601

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

alirezarezvani/claude-skills 29,725

Maintain interspect?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted