shashankreddy509

shashankreddy509/claude-tdd-kit

Plugin Claude Code

Plugin marketplace listing 2 plugins: dev-day, tdd-pipeline.

shashankreddy509/claude-tdd-kit

Plugin Claude Code

The complete developer day-loop for Claude Code + Jira: /start-session boots a senior-collaborator session (feedback memory, Jira backlog, standing plan-gate), /standup answers 'anything pending?', /bug-triage root-causes tickets, /groom preps them for estimation, /create-ticket files them, /jira-comment posts clean…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Investigate a Jira bug from its key to a root-cause verdict — classify bug-vs-feature, fan out read-only Explore agents across the repo, adversarially confirm the cause, and write a tasks/ -triage.md artifact a lean fix-planner can pick up. Orchestration only; read-only, never touches Jira, stops at verdict +…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Condense a grown feedback/memory file in place — shrink it 75-85% WITHOUT losing any distinct lesson. Merges points that mean the same thing, groups by theme, keeps every unique rule, concrete constant, and cross-reference. Use when the file has grown unwieldy, when the user says "feedback file is too big" / "shrink…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Create a Jira ticket in the current project from a short context blurb. Discovers the project's Jira config (cloudId + key) from its CLAUDE.md, fetches the real issue types, asks type then context, drafts a title + description (structured body for Bugs), shows the draft for inline edit, and creates only after explicit…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Captures this session's learnings — preferences, corrections, what worked, what to avoid — by merging them into feedback.md + project memory for future sessions. Utility/persistence skill: it records, it does not review or grade output. Trigger on /end-session or "end session".

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Pre-grooming analysis of a Jira ticket — produce a readiness + spec brief so the ticket can be groomed/estimated. Read-only; writes ONE artifact (tasks/ -grooming.md), touches no code and no Jira. Runs BEFORE a ticket is approved to work — answers "is this ready to estimate, and what will it touch", not "how do I…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Post a comment on a Jira ticket that renders cleanly despite the Atlassian MCP mangling markdown — strips bold/italic markers, indents code, keeps CC mentions verbatim. Use when the user says "post this on the ticket", "add a comment to PROJ-XXXX", "comment this on Jira", or after authoring an analysis/closure note to…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Synthesize this session's preferences/corrections into tasks/feedback.md and merge them into the existing file without ever deleting prior points. One job — the feedback artifact only. Called by end-session and by start-session's mid-session auto-capture; can also run standalone. Triggers: merge feedback, update…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Prove whether a build, compile, or test failure is caused by YOUR change or was already broken — by stashing your edits, re-running, and comparing. Read-only verdict; fixes nothing. Use when a build/test fails and the question is "is this my fault or pre-existing", or before blaming your diff. Triggers: is this my…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Read-only "anything pending?" sweep of live project state — git branch + dirty files, open PRs, the deploy gap (latest tag vs origin/main, app-code only), and open Jira issues (statusCategory != Done). Answers "what's left / anything pending / what's next" in one shot WITHOUT acting on anything. Use on '/standup'…

shashankreddy509/claude-tdd-kit

Skill Claude CodeCodex

Session-bootstrap orchestration skill — its one job is to bring a working session online: apply senior-collaborator operating parameters, load prior feedback, pull the project's Jira backlog, and activate the standing plan-gate (analysis + plan + approval before any code edit). Trigger on /start-session or "start…

shashankreddy509/claude-tdd-kit

Plugin Claude Code

Gated TDD build pipeline: /build plans a feature or bug fix and waits for click-approval; /implement runs the build-coordinator through test-writer → verify-red → implementer → test-runner → adversarially-verified code review → changelog (Critical findings hard-stop, post-review edits must re-pass review); /ship gates.

shashankreddy509/claude-tdd-kit

Agent

Spawned by the plugin's implement command after the user has approved a plan file (tasks/plans/ plan.md). The plan file path is passed as input. Orchestrates the full TDD pipeline in sequence: test-writer → implementer → test-runner (with retry loop) → code-review-coordinator, then STOPS at the ship gate (the commit…

shashankreddy509/claude-tdd-kit

Agent

Generates a conventional commit message from the STAGED diff, called by /ship after the commit has been scoped. Summarizes what changed, what files were affected, and why the feature was built (Why comes from the plan file). Output is ready to copy-paste into git commit.

shashankreddy509/claude-tdd-kit

Agent

Code quality and architecture reviewer. Checks for SOLID violations, dead code, complexity, bad patterns, missing error handling, and platform architecture anti-patterns.

shashankreddy509/claude-tdd-kit

Agent

Spawn this agent when the user runs the plugin's review command, on Stage 4 of the build pipeline (build-coordinator), or when asked for a code review. It reads the git diff, expands it with caller-context, spawns stack-appropriate specialist agents in parallel (including money-logic and concurrency reviewers)…

shashankreddy509/claude-tdd-kit

Agent

Concurrency & race-condition reviewer. Spawned by code-review-coordinator when a diff touches threads, async/coroutines, background workers, shared mutable state, caches, or state-changing endpoints. Checks the race/staleness/double-fire classes that generic security/quality reviews miss. Created after a…

shashankreddy509/claude-tdd-kit

Agent

Writes implementation code to make existing failing tests pass. Reads the plan file (path provided by the coordinator) and all test files before writing a single line.

shashankreddy509/claude-tdd-kit

Agent

Kotlin language best practices reviewer. Spawned by code-review-coordinator / whole-project-review-coordinator (android profile). Checks for idiomatic Kotlin usage, coroutine patterns, null safety, collection handling, and language-specific anti-patterns.

shashankreddy509/claude-tdd-kit

Agent

Memory and resource leak specialist. Spawned by code-review-coordinator. Checks for memory leaks, resource leaks, improper lifecycle handling, and platform-specific memory constraints.

shashankreddy509/claude-tdd-kit

Agent

Financial-correctness reviewer for ANY code that moves or computes money: payments, billing, checkout, subscriptions, refunds, invoicing, wallets, trading, orders, positions, prices, PnL. Spawned by code-review-coordinator when a diff touches such code. Checks the bug classes that a generic security/quality review…

shashankreddy509/claude-tdd-kit

Agent

Read-only research helper for feature planning. Reads the codebase, understands existing architecture, and returns a plan DRAFT as text to the main thread. Never writes any file and never writes implementation or test code.

shashankreddy509/claude-tdd-kit

Agent

Security-focused code reviewer. Spawned by code-review-coordinator. Checks for hardcoded secrets, injection vulnerabilities, insecure storage, improper authentication, exposed APIs, and platform-specific security issues.