Archive228/loopkit

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

753Stars on the repository
62Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

migration-writer

25

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Write safe, reversible database migrations for this repo's conventions. Use for any schema change.

753 +2 1mo ago A 22 tokens original MIT

model-routing

26

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.

753 +2 1mo ago A 33 tokens original MIT

owasp-review

27

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.

753 +2 1mo ago A 33 tokens original MIT

pdf-ingestion

28

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.

753 +2 1mo ago A 43 tokens original MIT

planner-spec-expand

29

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.

753 +2 1mo ago A 31 tokens original MIT

pr-from-diff

30

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Write a PR description a reviewer can approve fast. Use when opening any pull request.

753 +2 1mo ago A 22 tokens original MIT

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under a minute.

753 +2 1mo ago A 57 tokens original MIT

prompt-caching

32

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. Use when the system prompt, tool defs, or reference docs are stable across many turns.

753 +2 1mo ago A 44 tokens original MIT

read-the-trace

33

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.

753 +2 1mo ago A 29 tokens original MIT

readme-audit

34

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.

753 +2 1mo ago A 26 tokens original MIT

rebase-safely

35

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

36

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

37

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

38

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

39

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

40

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

41

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

42

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

43

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

44

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

45

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

753 +2 1mo ago A 19 tokens original MIT

structured-output

46

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

47

Archive228/loopkit

Skill Claude CodeCodex

Part of loopkit

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

Part of loopkit

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

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: