Archive228

63 mods across 3 repositories, 755 stars between them.

rebase-safely

49

Archive228/loopkit

Skill Claude CodeCodex

Rebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.

753 +2 1mo ago A 28 tokens original MIT

reduce-nesting

50

Archive228/loopkit

Skill Claude CodeCodex

Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.

753 +2 1mo ago A 28 tokens original MIT

revert-surgical

51

Archive228/loopkit

Skill Claude CodeCodex

Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.

753 +2 1mo ago A 0 tokens original MIT

schema-diff

52

Archive228/loopkit

Skill Claude CodeCodex

Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.

753 +2 1mo ago A 24 tokens original MIT

secret-scan

53

Archive228/loopkit

Skill Claude CodeCodex

Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.

753 +2 1mo ago A 29 tokens original MIT

self-eval-bias

54

Archive228/loopkit

Skill Claude CodeCodex

Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.

753 +2 1mo ago A 37 tokens original MIT

shift-notes

55

Archive228/loopkit

Skill Claude CodeCodex

Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.

753 +2 1mo ago A 47 tokens original MIT

simplify

56

Archive228/loopkit

Skill Claude CodeCodex

Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.

753 +2 1mo ago A 28 tokens original MIT

spec-first

57

Archive228/loopkit

Skill Claude CodeCodex

Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.

753 +2 1mo ago A 26 tokens original MIT

sprint-contract

58

Archive228/loopkit

Skill Claude CodeCodex

Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. Turns fuzzy specs into a testable target the evaluator can hold the generator to.

753 +2 1mo ago A 44 tokens original MIT

sql-review

59

Archive228/loopkit

Skill Claude CodeCodex

Review SQL and ORM queries for correctness, safety, and performance before they ship.

753 +2 1mo ago A 19 tokens original MIT

structured-output

60

Archive228/loopkit

Skill Claude CodeCodex

Get JSON out of the model reliably. Prefer tooluse with a schema over prompted-JSON, validate on receive, retry on parse fail. Use when downstream code will parse the response.

753 +2 1mo ago A 40 tokens original MIT

subagent-fanout

61

Archive228/loopkit

Skill Claude CodeCodex

Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.

753 +2 1mo ago A 34 tokens original MIT

Archive228/loopkit

Skill Claude CodeCodex

Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so featurelist.json stays immutable.

753 +2 1mo ago A 34 tokens original MIT

Archive228/loopkit

Skill Claude CodeCodex

Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.

753 +2 1mo ago A 36 tokens original MIT