Borrowing it
Nothing to install: this file belongs to vdaubry/bottega. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vdaubry/bottega/main/.claude/commands/code-delivery.mdgit clone --depth 1 https://github.com/vdaubry/bottegaWrote 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/commands/vdaubry/bottega/code-delivery)<a href="https://agentmods.dev/commands/vdaubry/bottega/code-delivery"><img src="https://agentmods.dev/badge/commands/vdaubry/bottega/code-delivery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/vdaubry/bottega/code-delivery"><img src="https://agentmods.dev/badge/commands/vdaubry/bottega/code-delivery.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.01230 |
| Opus 5.5 | $0.00015 | $0.00492 |
| Sonnet 5.5 | $0.00007 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
code-delivery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator of the code-delivery pipeline: a sequential chain of
coding agents that takes the plan for this branch all the way to an open pull
request, with no further input. It is the companion to /planification — that
command writes the plan; this one delivers it.
preflight ─▶ IMPLEMENTER ─▶ ( REVIEWER ⇄ IMPLEMENTER ) ─▶ REFINER ─▶ PR-MANAGER
Step 0 — Preflight & guard (REQUIRED — do this first)
The pipeline is driven by the plan file, computed deterministically (one plan per
worktree/branch — the same rule /planification uses):
leaf="$(git branch --show-current 2>/dev/null | sed 's#.*/##')"
[ -z "$leaf" ] && leaf="plan"
echo "tmp/plans/${leaf}.md"
If that file does not exist, STOP. Do not implement, do not branch, do not
open anything. Tell the user there is no plan for this branch and to run
/planification first. The pipeline must not start without a plan. It also needs
a real branch (a PR needs one), so it refuses to start on a detached HEAD.
How to run it
The pipeline is a self-contained Workflow at
.claude/workflows/code-delivery.js. Once the
plan exists, launch it as a single autonomous run:
Use the Workflow tool:
Workflow({ name: "code-delivery" }).
The Workflow re-runs the preflight guard itself (so it will refuse to start if the plan is missing), then runs every stage to completion — looping REVIEWER ⇄ IMPLEMENTER until the work passes review, refining, and opening the PR. Relay its final result (review status, iterations, PR URL, CI status) to the user.
If the Workflow tool is unavailable, execute the four stages sequentially in this
conversation instead, using the adapted prompts in the workflow file: spawn the
IMPLEMENTER, then the REVIEWER; on a NEEDS_WORK verdict loop back to the
IMPLEMENTER (up to MAX_REVIEW_ITERATIONS); on READY run the REFINER, then the
PR-MANAGER. Stop and report on BLOCKED or if the loop cap is hit — do not open a
PR on work that has not passed review.
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.
- 24d ago First seen · 82 lines · 37 tokens per session scan A 1fc6f4aead0e
code-delivery is a command published in the GitHub repository vdaubry/bottega (88 stars, last pushed 24d ago), licensed MIT. It adds 37 tokens to every session and 1,230 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.
Other commands, from other repositories
mach12:pr-pre-merge
Run the pre-merge checklist - branch freshness, docs, version, CHANGELOG, tests, CI.
mach12:pr-validation
Challenge a PR through independently assessed executable tests.
mach12:push
Commit, push, and post a progress comment using session context or branch detection.
commit
When you receive this command, do the following.
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.