A ticket implementation step that carries out the plan for a claimed work item in its Git worktree, a separate project directory tied to a branch. It makes incremental commits and runs type checks and tests after major steps.

Use it to continue a ticket already picked up by Ticket-Flow and turn its approved plan into code, commits, and tested changes.

It keeps implementation work tied to the correct ticket and branch, while catching errors during the work instead of at the end.

implement — Skill by keefar

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/keefar/ticket-flow/implement

Any agent

npx skills add keefar/ticket-flow --skill implement

Clone the repo

git clone --depth 1 https://github.com/keefar/ticket-flow

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,480 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00055	$0.02480
Opus 5	$0.00028	$0.01240
Sonnet 5	$0.00011	$0.00496
Haiku 4.5	$0.00006	$0.00248

Measured yesterday against content hash 69fed5c54a67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/implement/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ticket-flow:implement — Phase 2 of Ticket-Flow

Args: none — operates in the current worktree, derives the item via the branch: marker in the bd notes field.

Prerequisites

/ticket-flow:pickup has been run (item is In Progress, worktree exists, branch: marker set)
Current directory = worktree (or the user is asked to switch)

Steps

1. Find the current branch + item

git branch --show-current

→ branch name (e.g. worktree-94-multipoint-messung from EnterWorktree, or feature/94-multipoint-messung from manual git worktree).

Resolve the item by the .ticket-flow mode flag (source skills/kanban/bd-helper.sh):

Find the bd issue whose notes field carries branch: <branch>. Do not read KANBAN.md.

source "${CLAUDE_PLUGIN_ROOT}/skills/kanban/bd-helper.sh"
BRANCH="$(git branch --show-current)"
BD_ID="$(bd list --json 2>/dev/null | jq -r --arg b "$BRANCH" \
  '.[] | select((.notes // "") | test("(^|\\n)branch: " + $b + "$")) | .id' | head -1)"
ID="$(bd_kanban_for "$BD_ID")"

IMPORTANT — where a git commit may run depends on the session type. Two different regimes, do not mix them up:

Worktree-isolated session — a subagent dispatched with isolation: "worktree", or this session after EnterWorktree. Git against the main repo is refused outright, in both spellings: cd <main-repo> && git … and git -C <main-repo> are rejected with "this command changes directory to the shared checkout … before running git. Refusing to run it". There is no workaround and no point burning calls on one. Commit to the worktree branch only; every main-repo write — ticket state, .beads/ export commits, the merge — belongs to the controller or a main-repo session. That is exactly how /ticket-flow:flow --parallel splits the work (see flow P3/P6: only the controller ever writes ticket state).
Non-isolated session inside a worktree — an external worktree adopted via /ticket-flow:pickup --here (orca card, Conductor, worktrunk, bead-workflow-skills) is a normal session that merely happens to sit in a linked worktree. There, main-repo git works, but only as a single shell statement with dangerouslyDisableSandbox: true:

Read the full file on GitHub · 168 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 168 lines · 0 tokens per session scan A 69fed5c54a67

Subscribe to this mod's changes

implement is a skill published in the GitHub repository keefar/ticket-flow (4 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 2,480 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Project management Testing claude-code git-worktree kanban plugin workflow

kanvibe-release-deploy

Use this skill whenever releasing or deploying KanVibe desktop from a clean, up-to-date dev checkout: ask only for the target version and release-note approval, then let the AI update package versions, run pnpm run deploy, publish the DMG GitHub release, update the Homebrew cask, create the release PR, and auto-merge…

rookedsysc/kanvibe · 112 tokens

council-router

Route code reviews to appropriate council members. Use when reviewing PRs, architecture decisions, or significant code changes that need expert perspective.

automagik-dev/forge · 31 tokens

codekanban-cli

Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command. Use when the user wants to create, inspect, control, watch, or continue CodeKanban AI work from a project path, project ID, or project name without relying on repository-local helper scripts. Prefer…

fy0/CodeKanban · 102 tokens

implement