pandysp/claude-plugins

5Stars on the repository
39Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

pandysp

01

pandysp/claude-plugins

Plugin Claude Code

Plugin marketplace listing 18 plugins: second-opinion, preflight, verify-result, verify-claims, pre-mortem.

5 10d ago A tokens not measured original MIT

align

02

pandysp/claude-plugins

Plugin Claude Code

Surface what I think we're doing before acting on it. Produces a structured manifest exposing every silent commitment so the user can correct course before any artifact is produced.

5 10d ago A tokens not measured original MIT

clarify

03

pandysp/claude-plugins

Plugin Claude Code

Surface and resolve underspecified decisions before designing. Asks targeted questions about scope, edge behavior, trade-offs, integration, constraints, and audience (with defaults), so design choices aren't silently locked around hidden assumptions.

5 10d ago A tokens not measured original MIT

design-options

04

pandysp/claude-plugins

Plugin Claude Code

Generate multiple strong design options with explicit tradeoff profiles, anchored against at least two ideal target architectures.

5 10d ago A tokens not measured original MIT

drive-browser

05

pandysp/claude-plugins

Plugin Claude Code

Drive a browser with Playwright as a dual-mode superset. Resilient locators for debugging your own web app and a vision/coordinate loop for opaque real sites, on a fresh browser or the user's real logged-in session.

5 10d ago A tokens not measured original MIT

explore

06

pandysp/claude-plugins

Plugin Claude Code

Map the terrain before designing: locate, trace, pattern, constrain. Used before any substantive design or planning step. Output is mostly for the agent's grounding; only surprises and hard constraints surface to the user.

5 10d ago A tokens not measured original MIT

handoff

07

pandysp/claude-plugins

Plugin Claude Code

Write a durable handoff for work that's about to ship: structured PR descriptions, summaries, memos, or memory notes. Tells the next reader what was built, why, what changed, and what's next, without forcing them to dig through the diff.

5 10d ago A tokens not measured original MIT

pre-mortem

08

pandysp/claude-plugins

Plugin Claude Code

Systematically identify how a plan or design could fail before committing to it.

5 10d ago A tokens not measured original MIT

preflight

09

pandysp/claude-plugins

Plugin Claude Code

Honest self-assessment skill that surfaces incomplete work, missing verifications, bugs, and improvement ideas before shipping.

5 10d ago A tokens not measured original MIT

quality-review

10

pandysp/claude-plugins

Plugin Claude Code

Multi-lens quality audit for docs, code, and other artifacts. 13 quality adjectives as audit lenses with per-domain translation sheets, a workflow-backed finder/verifier pipeline, and lens-yield reporting.

5 10d ago A tokens not measured original MIT

reflect

11

pandysp/claude-plugins

Plugin Claude Code

Capture durable lessons from a session before they fade, routing each insight to the applicable instructions, memory, project notes, or tooling ticket.

5 10d ago A tokens not measured original MIT

second-opinion

12

pandysp/claude-plugins

Plugin Claude Code

Get an independent review through the strongest available channel before presenting non-trivial reasoning to the user.

5 10d ago A tokens not measured original MIT

silent-failures

13

pandysp/claude-plugins

Plugin Claude Code

Audit error handling for silent failures, inadequate feedback, and inappropriate fallbacks using one canonical methodology and the strongest isolated reviewer available.

5 10d ago A tokens not measured original MIT

spec

14

pandysp/claude-plugins

Plugin Claude Code

Write the implementation spec (context, approach, files to modify, utilities to reuse, and verification) that drives execution after design is chosen.

5 10d ago A tokens not measured original MIT

pandysp/claude-plugins

Plugin Claude Code

Before flipping a previously-stated position under pressure, restate its strongest form and the goal it served, then check whether the trigger refutes the core on the same goal, not just a decorative argument or a different axis.

5 10d ago A tokens not measured original MIT

understudy

16

pandysp/claude-plugins

Plugin Claude Code

Write code, comments, tests, or commit messages that read as if the project's own maintainer wrote them, so a contribution is accepted as native rather than rejected as foreign. A foreign-looking patch is a cost to the maintainer even when it's correct.

5 10d ago A tokens not measured original MIT

verify-claims

17

pandysp/claude-plugins

Plugin Claude Code

Identify and verify unverified claims in the agent's own responses before presenting them as conclusions.

5 10d ago A tokens not measured original MIT

verify-result

18

pandysp/claude-plugins

Plugin Claude Code

Black-box verification of any agent output: code, documents, presentations, reports, configs. Examine from the consumer's perspective and show evidence.

5 10d ago A tokens not measured original MIT

worktrunk-hook

19

pandysp/claude-plugins

Plugin Claude Code

Route Claude Code's auto-created git worktrees through worktrunk so background and --worktree sessions inherit project hooks (env symlinks, installs, port allocation).

5 10d ago A tokens not measured original MIT