vidhunnan

41 mods across 1 repository, 2 stars between them.

agentic-skills

01

vidhunnan/agentic-skills

Plugin Claude Code

Plugin marketplace listing 20 plugins: handoff-generator, changelog-tracker, model-strategy, branch-naming, repo-setup.

2 2d ago A tokens not measured original MIT

vidhunnan/agentic-skills

Instructions file

Claude Code instructions for vidhunnan/agentic-skills, covering claude.md, what this repo is, layout & conventions, multi-surface design (the core architectural constraint) and skill protocols — the claude.md registration pattern.

2 2d ago A 3,535 tokens original MIT

branch-naming

03

vidhunnan/agentic-skills

Skill Claude CodeCodex

Suggests and optionally creates a context-appropriate git branch name that follows the project's convention. Reads the convention from CLAUDE.md, else infers it from existing branches, else helps you define one. Use when the user says "create a branch", "start work on X", "what should I name this branch", "name this…

2 2d ago A 88 tokens original MIT

changelog-tracker

04

vidhunnan/agentic-skills

Plugin Claude Code

Documents every substantive commit into per-commit changelog files plus a rolling CHANGELOG index.

2 2d ago A tokens not measured original MIT

changelog-tracker

05

vidhunnan/agentic-skills

Skill Claude CodeCodex

Documents every substantive commit into a per-commit changelog file plus a rolling CHANGELOG index, mirroring a Keep-a-Changelog layout. Use after Claude makes a commit, or when the user says "update the changelog", "document this commit", "log this commit", "changelog this", or runs /changelog-tracker. Claude Code…

2 2d ago A 84 tokens original MIT

decisions-logger

06

vidhunnan/agentic-skills

Plugin Claude Code

Mines a project for the decisions that were actually made and writes each as a numbered ADR with its evidence — asking when the "why" was never written down, and never inventing one.

2 2d ago A tokens not measured original MIT

decisions-logger

07

vidhunnan/agentic-skills

Skill Claude CodeCodex

Mines a project for the architectural and process decisions that were actually made and writes each as a numbered ADR into docs/decisions/ — with evidence citations, an index table plus supersession graph, and append-only follow-ups. Proposes candidates with their sources and asks when the "why" was never written…

2 2d ago A 135 tokens original MIT

design-brief

08

vidhunnan/agentic-skills

Plugin Claude Code

Interviews you into a short, structured design brief — problem, who feels it, jobs to be done, constraints, success criteria and non-goals — and marks what wasn't stated rather than inventing it.

2 2d ago A tokens not measured original MIT

design-brief

09

vidhunnan/agentic-skills

Skill Claude CodeCodex

Interviews you into a short, structured design brief — the problem, who feels it, jobs to be done, constraints, what success looks like, and the non-goals — then writes it to the briefs tier so later critique and decisions have a stated intent to cite. Captures what you actually hold and marks what you don't, rather…

2 2d ago A 136 tokens original MIT

design-critique

10

vidhunnan/agentic-skills

Plugin Claude Code

Reviews a built interface against its stated design intent — naming how the thing reads before proposing a fix, ranking findings by severity, and treating removal as a first-class verdict. Refuses to critique without a written intent.

2 2d ago A tokens not measured original MIT

design-critique

11

vidhunnan/agentic-skills

Skill Claude CodeCodex

Reviews a built interface against its stated design intent — naming how the thing reads before proposing any fix, ranking findings by severity, and treating removal as a first-class verdict rather than an afterthought. Refuses to critique without a written intent, because critique against nothing is just taste with…

2 2d ago A 124 tokens original MIT

design-decisions

12

vidhunnan/agentic-skills

Plugin Claude Code

Records a design fork as a numbered, append-only ADR — options, what was chosen, what was given up, and what would make us revisit — and never invents a rationale.

2 2d ago A tokens not measured original MIT

design-decisions

13

vidhunnan/agentic-skills

Skill Claude CodeCodex

Records a design fork as a numbered, append-only ADR in the design decisions tier — the options, what was chosen, what was given up, and what would make us revisit — with an index and supersession handling. Captures the reasoning while it still exists, and writes "(reason not stated)" rather than inventing one. Use…

2 2d ago A 131 tokens original MIT

design-explore

14

vidhunnan/agentic-skills

Plugin Claude Code

Generates three genuinely distinct design directions from a written visual direction — each committed to a named structural axis, each with its thesis, bet and risk — ending in a comparison matrix you judge by eye. Never records the verdict.

2 2d ago A tokens not measured original MIT

design-explore

15

vidhunnan/agentic-skills

Skill Claude CodeCodex

Generates three genuinely distinct design directions from a written visual direction — each committed to a named structural axis, each carrying its thesis, its bet and its risk, ending in a comparison matrix you can judge by eye rather than by description. Refuses to generate against nothing, and refuses to ship three…

2 2d ago A 138 tokens original MIT

design-language

16

vidhunnan/agentic-skills

Plugin Claude Code

Interviews you into a written visual direction — the surface and its brand posture, the references and the anti-reference, the constraints as breakable rules, and the vocabulary — and asks what you want rather than proposing a look for you.

2 2d ago A tokens not measured original MIT

design-language

17

vidhunnan/agentic-skills

Skill Claude CodeCodex

Interviews you into a written visual direction — the surface and whether it wears the brand, the references you're pulling from and the one you're explicitly not, the hard constraints stated as rules that can be broken, and the vocabulary that's in and out of bounds — then writes it to the system tier so exploration…

2 2d ago A 150 tokens original MIT

design-setup

18

vidhunnan/agentic-skills

Plugin Claude Code

Scaffolds a project's design context stack — briefs, research, explorations, decisions, specs, system — and registers the routing table in CLAUDE.md.

2 2d ago A tokens not measured original MIT

design-setup

19

vidhunnan/agentic-skills

Skill Claude CodeCodex

Scaffolds a project's design context stack — the tiered folders (briefs, research, explorations, decisions, specs, system) that let an agent or a new teammate be briefed on design work the way git briefs them on code. Surveys what already exists, adopts your existing folder names, writes only the gaps, and registers…

2 2d ago A 138 tokens original MIT

exploration-log

20

vidhunnan/agentic-skills

Plugin Claude Code

Records a round of design iteration — what it tested, what changed, what was learned, and whether it was kept, killed or parked — append-only, and answers "have we tried this before?" from the log.

2 2d ago A tokens not measured original MIT

exploration-log

21

vidhunnan/agentic-skills

Skill Claude CodeCodex

Records a round of design iteration into the explorations tier — what it was testing, what changed, what was learned, and whether it was kept, killed or parked, with the reason. Append-only, so a direction you abandoned is still readable a year later. Also answers "have we tried this before?" from the log. Use when…

2 2d ago A 126 tokens original MIT

handoff-generator

22

vidhunnan/agentic-skills

Plugin Claude Code

Interactive, bidirectional Chat↔Code generator for a comprehensive project handoff — progress, features, decisions, changelog, next actions, and a near-verbatim session log.

2 2d ago A tokens not measured original MIT

handoff-generator

23

vidhunnan/agentic-skills

Skill Claude CodeCodex

Interactive, bidirectional generator for a comprehensive project handoff that bridges Claude.ai chat and Claude Code. Interviews the user first, then writes a structured handoff covering the project's progress, timeline, features, decisions, changelog delta, open questions, next actions, and a near-verbatim log of the…

2 2d ago A 152 tokens original MIT

model-strategy

24

vidhunnan/agentic-skills

Plugin Claude Code

Creates and maintains docs/MODEL-STRATEGY.md — which Claude model to use for which work, tailored via interview.

2 2d ago A tokens not measured original MIT