manishiitg

131 mods across 2 repositories, 15 stars between them.

review-code

73

manishiitg/coding-agent-loop

Command Claude Code

Call getworkflowcommandguidance(kind="design-plan", focus="Architecture focus: inspect saved scripts against their current step objectives, input/output contracts, and relevant retained behavior. Propose improvements without applying them.

not rated 13 19d ago A 0 tokens original MIT

setup-goals

74

manishiitg/coding-agent-loop

Command Claude Code

Call getworkflowcommandguidance(kind="setup-goals", focus="{{context}}") and follow the returned instructions verbatim. Treat focus as the conversation/request context that appeared before the slash command, including the user's recent constraints and intent. The tool returns the canonical guided-flow text for this…

not rated 13 19d ago A 0 tokens original MIT

agentworks

75

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Read and run AgentWorks workflows and Crews through MCP (list workflows, read files, plans, runs, guidance, and knowledge; execute steps, workflows, and schedules; ask Crews and call their functions). Load when the task touches an AgentWorks workflow or when AgentWorks MCP tools are available.

not rated 13 changed 19d ago A 64 tokens original MIT

update-memory

76

manishiitg/coding-agent-loop

Command Claude Code

Review this conversation and persist what is worth keeping as durable project knowledge — both memory and skills.

not rated 13 19d ago A 0 tokens original MIT

work-ui-control

77

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Present the correct Crew project panel with acknowledged UI control. Use when opening, refreshing, or checking a Crew workspace view; do not use Workflow view IDs or semantics.

not rated 13 19d ago A 37 tokens original MIT

manishiitg/coding-agent-loop

Command Claude Code

Run the /run-architecture-review pass as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Architecture review", completionmode "presentresult", and this instruction.

not rated 13 19d ago A 0 tokens original MIT

run-goal-work

79

manishiitg/coding-agent-loop

Command Claude Code

Run the /run-goal-work pass as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Goal Work pass", completionmode "presentresult", and this instruction.

not rated 13 19d ago A 0 tokens original MIT

run-plan-drift

80

manishiitg/coding-agent-loop

Command Claude Code

Run the /run-plan-drift review as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Plan Drift review", completionmode "presentresult", and this instruction.

not rated 13 19d ago A 0 tokens original MIT

manishiitg/coding-agent-loop

Command Claude Code

Run /run-technical-review as a BACKGROUND task so this chat stays responsive. If the runinbackground tool is available: call runinbackground with name "Technical review + fix", completionmode "presentresult", the review instruction below, and a messagesequence with one follow-up message (id "fix") carrying the fix…

not rated 13 19d ago A 0 tokens original MIT

daily-learnings

82

manishiitg/coding-agent-loop

Command Claude Code

Do this Crew's end-of-day learning review: read today's conversations, then save what is new and worth keeping into memory and skills.

not rated 13 19d ago A 0 tokens original MIT

finance-analyst

84

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Set up a Finance Analyst Crew, analyze authorized business finance records, and prepare sourced briefs with transparent calculations.

not rated 13 19d ago A 26 tokens original MIT

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Prepare a source-linked subscription revenue close review with reconciliations, deferred-revenue questions, and an exception list.

not rated 13 19d ago A 30 tokens original MIT

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Review vendor bills, subscriptions, company card charges, and expenses against approval policy with a source-linked payables queue.

not rated 13 19d ago A 30 tokens original MIT

tax-export

87

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Prepare traceable transaction exports and exception lists for review by a business and its tax professional.

not rated 13 19d ago A 21 tokens original MIT

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Audit an authorized new website, identify evidence-backed traffic opportunities, and prepare a practical 30-day growth plan.

not rated 13 19d ago A 27 tokens original MIT

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Build a chat-led customer onboarding route with owned milestones, verified first-value evidence, and optional account health review.

not rated 13 19d ago A 29 tokens original MIT

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Build a chat-led multi-Crew SaaS finance review with source-linked billing exceptions, finance impact, and validated handoffs.

not rated 13 19d ago A 30 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: