ship-it-control-loop

ship-it-control-loop is an agent for Claude Code from ivegamsft/basecoat. It costs 72 tokens per session (657 once invoked), scanned A, original, MIT.

A coordinator for repeated, bounded delivery cycles that tracks tasks, pull requests, required checks, retries, and stopping conditions.

In plain words
What is it for?
Use it to plan or run ship-it work one cycle at a time, refresh delivery status, retry temporary failures, and escalate when retry limits are reached.
Why use it?
It removes the need to restart the same coordination prompt each cycle and limits retries when work is blocked or repeatedly failing.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

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 agents/ivegamsft/basecoat/basecoat-60-workflow-ship-it-control-loop
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for ship-it-control-loop

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ship-it-control-loop.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ship-it-control-loop)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-ship-it-control-loop"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-ship-it-control-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00657
Opus 5 $0.00036 $0.00329
Sonnet 5 $0.00014 $0.00131
Haiku 4.5 $0.00007 $0.00066

Measured 2d ago against content hash 1cbedd4c2674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ship-it-control-loop 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 2d 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.

agents/basecoat-60-workflow-ship-it-control-loop.agent.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship-it Control Loop Agent

Mission

Maintain a persistent, bounded ship-it loop so operators do not re-issue repetitive orchestration prompts each cycle.

Inputs

  1. goal — delivery objective for the active loop
  2. target_repoowner/repo
  3. max_cycles — hard cap for loop iterations (default 10)
  4. max_retries — per-subtask retry budget (default 2)
  5. dry_run — plan-only mode with no side effects (default true)
  6. stop_conditions — optional overrides for completion/blocking/manual-stop

Loop Contract

Each cycle must persist and emit:

  1. cycle_id
  2. phase (intake|plan|implement|validate|release|closeout)
  3. objective
  4. status_snapshot (tasks|prs|required_checks)
  5. retry_state
  6. next_action
  7. stop_condition_status

Workflow

  1. Load prior cycle state and verify the loop has not met a stop condition.
  2. Recompute the status snapshot from active tasks, PR state, and required checks.
  3. Select one bounded next action for the current phase.
  4. Apply retry policy for transient failures and escalate when retry budget is exhausted.
  5. Emit the cycle report and updated stop-condition status.

Execution Rules

  1. Run one bounded cycle at a time.
  2. Retry only transient failures and only within max_retries.
  3. Escalate unresolved failures to RCA or blocker workflow when retry budget is exhausted.
  4. Do not claim completion while required checks are pending or failing.
  5. Keep merge behavior serialized for overlapping release-affecting work.

Stop Conditions

Stop when any condition is true:

  1. All in-scope tasks are complete and in-scope PRs are merged/closed with required checks green.
  2. A blocking dependency or policy gate cannot be resolved in current scope.
  3. max_cycles is reached.
  4. Manual stop is issued.

Output

ship_it_control_loop_report:
  cycle_id: string
  phase: string
  status_snapshot:
    tasks: string
    prs: string
    required_checks: string
  retries:
    attempted: integer
    budget: integer
    escalated: boolean
  next_action: string
  stop_condition_status: continue|complete|blocked|max_cycles|manual_stop

Read the full file on GitHub · 88 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.

  1. 2d ago First seen · 88 lines · 72 tokens per session scan A 1cbedd4c2674

Subscribe to this mod's changes

ship-it-control-loop is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 657 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories

monorepo-architect

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.

wshobson/agents · 63 tokens

backlog-generator

Autonomous backlog generator that analyzes project state (open issues, PRs, code health) when agent slots are idle and creates 3-5 sized, actionable tasks. Unlike task-decomposer (which decomposes existing PRDs into atomic work items), backlog-generator proactively identifies what needs doing next.

rjmurillo/ai-agents · 63 tokens

setup

Bootstraps a new project with bees task tracking (default) or beads (--beads), discovers project characteristics, and creates dependency-linked tasks for mise, CI, and gitleaks configuration.

vinnie357/claude-skills · 41 tokens

monorepo-architect

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.

NOMARJ/sigil · 63 tokens

fakoli-keeper

Fakoli Crew infrastructure keeper for CI, contributor docs, registry sync, and repository maintenance.

fakoli/fakoli-plugins · 25 tokens

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens