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.
npx agentmods add skills/keefar/ticket-flow/finishnpx skills add keefar/ticket-flow --skill finishgit clone --depth 1 https://github.com/keefar/ticket-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/keefar/ticket-flow/finish)<a href="https://agentmods.dev/skills/keefar/ticket-flow/finish"><img src="https://agentmods.dev/badge/skills/keefar/ticket-flow/finish.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00068 | $0.07490 |
| Opus 5 | $0.00034 | $0.03745 |
| Sonnet 5 | $0.00014 | $0.01498 |
| Haiku 4.5 | $0.00007 | $0.00749 |
Grade C, and why
finish scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Path still listed** → real error. **Stop and hand it to the user — never delete the directory yourself.** Forcing the removal (`shutil.rmtree`, `rm -rf`) is precisely the fallback Claude Code removed in 2.1.143, to p How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ticket-flow:finish — Phase 3 of Ticket-Flow
Args: none — operates in the current worktree, derives the item via the
branch: marker in the bd notes field.
Prerequisites
- /ticket-flow:implement is complete (all ACs met, commits made)
- Current directory = worktree
- Typecheck/tests green
Steps
1. Identify the item
Read the current branch (git branch --show-current), then find the bd issue
whose notes field carries branch: <branch>. Do not read KANBAN.md.
source "${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")"
Extract ID, title, tag, spec/plan links from the resolved issue. Also read a worktree: external <path> line in the bd notes — it means the worktree was adopted via /ticket-flow:pickup --here (orca, Conductor, worktrunk, bead-workflow-skills): set ADOPTED=1, WORKTREE=<path>; 5a and Step 7 branch on it.
Commit-cwd caveat (full form in /ticket-flow:implement Step 1) — the rule differs by session type:
- Worktree-isolated session (a dispatched
isolation: "worktree"agent, or this session afterEnterWorktree): git against the main repo is refused outright,cd <main-repo> && git …andgit -C <main-repo>alike ("Refusing to run it"). So the main-repo half of Steps 5–6 does not happen here: either afterExitWorktreefrom the main-repo session (5a), or — in--parallel/--serial— in the controller, which is the only writer of ticket state. - Non-isolated session in an adopted worktree (
ADOPTED=1, from/ticket-flow:pickup --here): main-repo git works as a single statementcd <main-repo> && git …withdangerouslyDisableSandbox: true;git -Calone hits.git/index.lock: Operation not permitted.
In both cases, commits to the worktree branch run from the worktree root, not a subdirectory.
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.
- 4d ago First seen · 326 lines · 68 tokens per session scan C d1b35c10cdd7
finish is a skill published in the GitHub repository keefar/ticket-flow (4 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 7,490 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flow-next-interview
In-depth Q&A to refine a spec, task, or spec file before building. Use when asked to flesh out, refine, or interrogate requirements.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
flow-next-drive
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-make-pr
Open a PR with a cognitive-aid body rendered from flow-next spec state via gh. Use whenever asked to make or open a PR in a flow-next repo.
flow-next-pilot
Single-tick autonomous build-loop conductor. One spec or the backlog, one stage per tick (pipeline.chainStages chains qa into make-pr), emits PILOTVERDICT. Use when asked to pilot a spec or backlog.