{"slug":"compounded","title":"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.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-08T06:00:01.054Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ankitkr3/compounded.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"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."}]}}