compounded
Ankit Kumar
compounded turns Claude Code skills into a trust-gradient system: every skill earns its autonomy through demonstrated reliability. New skills the agent proposes start as .proposed/, get replayed on...
From the developer
License
MIT
Works with
Claude Code
Description
From the marketplace listing
compounded turns Claude Code skills into a trust-gradient system: every skill earns its autonomy through demonstrated reliability. New skills the agent proposes start as .proposed/, get replayed on a real follow-up task by a verifier subagent (Haiku 4.5) to graduate to .verified/, build a track record to reach .trusted/, and finally graduate to .autonomous/ after 10+ uses with a clean recent run. One correction sends a skill back a tier. Three corrections in 30 days drop it to .proposed. Includes cross-project memory (a user-global USER.md auto-injected into every session) and a portable .tar.gz archive for moving your earned skills across machines. v1.1 adds an auto-proposer hook that scores each turn (tool calls, distinct file edits, recovery from failure) and nudges the agent to save high-signal procedures — so you don't have to remember to ask. No daemon. No cloud. No telemetry. Python stdlib only. All state in ~/.claude/compounded/ (SQLite + flat files). MIT licensed.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
An end-to-end web novel production system built on Claude Code. Combines 18 specialist agents and 10 skills to automate the full pipeline...
Shared terms: propose, system, agent, code
-
PushNotifiMe enables human-in-the-loop notifications and approvals for AI agents, developer workflows, and autonomous systems. Send real-...
Shared terms: system, real, agent, autonomous
-
Claude Code + Cursor Agent orchestration system. Delegates coding tasks to Cursor Agent via ACP bridge with Phase 0-8 pipeline.
Shared terms: system, task, agent, code
-
Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a h...
Shared terms: system, task, agent, code
-
AI Agent Team Operating System for Claude Code. Provides persistent team management, meeting collaboration, task wall with pipeline workf...
Shared terms: system, task, agent, code
Keywords
Files & skills
compounded · catalog manifest
Saved declaration
{}
compounded · catalog manifest
Saved declaration
{
"name": "compounded",
"source": {
"sha": "9feb7586e826028afa6492debd4ec06ecdf86f02",
"url": "https://github.com/ankitkr3/compounded.git",
"source": "url"
},
"homepage": "https://github.com/ankitkr3/compounded",
"description": "compounded turns Claude Code skills into a trust-gradient system: every skill earns its autonomy through demonstrated reliability. New skills the agent proposes start as .proposed/, get replayed on a real follow-up task by a verifier subagent (Haiku 4.5) to graduate to .verified/, build a track record to reach .trusted/, and finally graduate to .autonomous/ after 10+ uses with a clean recent run. One correction sends a skill back a tier. Three corrections in 30 days drop it to .proposed.\n\nIncludes cross-project memory (a user-global USER.md auto-injected into every session) and a portable .tar.gz archive for moving your earned skills across machines. v1.1 adds an auto-proposer hook that scores each turn (tool calls, distinct file edits, recovery from failure) and nudges the agent to save high-signal procedures — so you don't have to remember to ask.\n\nNo daemon. No cloud. No telemetry. Python stdlib only. All state in ~/.claude/compounded/ (SQLite + flat files). MIT licensed."
}
compounded · catalog manifest
Saved declaration
{
"name": "compounded",
"author": {
"url": "https://github.com/ankitkr3",
"name": "Ankit Kumar"
},
"$schema": "https://json.schemastore.org/claude-code-plugin.json",
"license": "MIT",
"homepage": "https://github.com/ankitkr3/compounded",
"keywords": [
"memory",
"skills",
"self-improving",
"trust-gradient",
"earned-autonomy",
"verified-skills",
"local-first"
],
"repository": "https://github.com/ankitkr3/compounded",
"description": "Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud."
}
plugin.json observed Nov 6, 2026 · 10:42 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install compounded@claude-community
Technical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 00:08 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: served from cache. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.