agent
01Command Claude Code
Create or improve a focused agent definition. Use when a new role is needed. Output: a registered agents/ .md.
not rated 0 3mo ago A 28 tokens
original MIT
0Stars on the repository
170Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Command Claude Code
Inspect the repository with AI reasoning and build an evidence-backed context pack under .agent/context/. Use after setup or major architecture changes. Output: routing, architecture, modules, flows, data, commands, tests, and risks.
not rated 0 3mo ago A 49 tokens
original MIT
Command Claude Code
Summarize large context without losing critical facts. Use when output is noisy or near a context limit. Output: a compact, fact-preserving summary.
not rated 0 3mo ago A 36 tokens
original MIT
council
04Command Claude Code
Turn an ambiguous request into an evidence-backed recommendation via discovery, adaptive specialist review, one challenge round, and chair synthesis. Use for high-uncertainty or high-impact decisions. Output: a decision record; stops for approval, then hands to /spec.
not rated 0 3mo ago A 58 tokens
original MIT
debug
05Command Claude Code
Reproduce, isolate, and fix a failure through a bounded root-cause loop. Use for bugs, crashes, flaky tests, regressions, or incorrect behavior. Output: a verified minimal fix or an evidence-backed blocked report.
not rated 0 3mo ago A 50 tokens
original MIT
fix
06Command Claude Code
Fix only the blocking findings from a review, with no unrelated work. Use after /review. Output: a minimal diff that clears blockers with green gates.
not rated 0 3mo ago A 34 tokens
original MIT
Command Claude Code
Design and implement a new frontend surface through one intentional, design-system-aware, responsive, accessible, browser-validated pass.
not rated 0 3mo ago A 27 tokens
original MIT
Command Claude Code
Implement an approved frontend-redesign spec with one coherent writer, browser comparison, and independent visual, UX, interaction, accessibility, and validation specialists.
not rated 0 3mo ago A 34 tokens
original MIT
implement
09Command Claude Code
Implement an approved spec with the smallest reasonable diff, tests, and passing gates. Use after approval. Output: a focused diff and a gate summary.
not rated 0 3mo ago A 33 tokens
original MIT
Command Claude Code
Audit and improve an existing interface through one evidence-backed, design-system-aware implementation and browser-verification pass.
not rated 0 3mo ago A 27 tokens
original MIT
invoke
11Command Claude Code
Interpret an open-ended request and route it to the right HarnessKit command, loop, or specialized agent.
not rated 0 3mo ago A 23 tokens
original MIT
pack
12Command Claude Code
Explain or change behavior-pack configuration. Use to inspect or toggle packs. Output: updated pack state and regenerated exports.
not rated 0 3mo ago A 25 tokens
original MIT
Command Claude Code
Audit an existing web page for purposeful image and illustration opportunities, then write an approval-gated three-tier asset spec with one coherent style and generation-ready prompts, dimensions, and delivery metadata.
not rated 0 3mo ago A 46 tokens
original MIT
review
14Command Claude Code
Review the diff against the spec for correctness, regressions, and missing tests. Use after implementation. Output: labelled findings and a verdict.
not rated 0 3mo ago A 31 tokens
original MIT
Command Claude Code
Create a highly detailed specification through deeper discovery and a larger, structured question batch before approval.
not rated 0 3mo ago A 22 tokens
original MIT
Command Claude Code
Produce an approval-gated, browser-evidenced redesign specification for an existing frontend surface using independent UX, visual, interaction, design-system, accessibility, and validation specialists.
not rated 0 3mo ago A 39 tokens
original MIT
spec
17Command Claude Code
Adaptively create a reviewable specification: inspect context, ask minimal blockers, consult selected specialists when useful, then wait for approval.
not rated 0 3mo ago A 30 tokens
original MIT
sum-spec
18Command Claude Code
Explain an existing specification in concise plain language before approval. Use after /spec or whenever a developer needs to understand a spec quickly.
not rated 0 3mo ago A 29 tokens
original MIT
ui-review
19Command Claude Code
Run an actionable UX and accessibility review of user-facing changes. Use for UI work. Output: prioritized blocking issues and polish.
not rated 0 3mo ago A 29 tokens
original MIT
Command Claude CodeCursor
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
not rated 0 3mo ago A 0 tokens
original MIT
Command Claude CodeCursor
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
not rated 0 3mo ago A 0 tokens
copy · 88% MIT
Command Claude CodeCursor
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
not rated 0 3mo ago A 0 tokens
original MIT
Command Claude CodeCursor
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
not rated 0 3mo ago A 0 tokens
copy · 77% MIT
Command Claude CodeCursor
Follow this ordered workflow. Respect every human-approval gate and stop when instructed.
not rated 0 3mo ago A 0 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: