flow.run.cycle

A workflow skill for processing tasks one at a time through the repository's FLOW process. It only starts the next task after the previous task's pull request has passed all required continuous-integration checks.

In plain words
What is it for?
Use it to run a workplan as a sequence of task branches and pull requests. It also helps resume in-progress work, review checks, fix failures, and continue only when the checks are green.
Why use it?
It prevents several unfinished branches from advancing at once and stops later work from building on code that has not passed automated checks.

Skill for Claude CodeCodex

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/soundblaster/xcodemcpwrapper/flow.run.cycle
Any agent
npx skills add SoundBlaster/XcodeMCPWrapper --skill flow.run.cycle
Clone the repo
git clone --depth 1 https://github.com/SoundBlaster/XcodeMCPWrapper

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 571 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 $0.00066 $0.00571
Opus 5 $0.00033 $0.00285
Sonnet 5 $0.00013 $0.00114
Haiku 4.5 $0.00007 $0.00057

Measured 2d ago against content hash fd3b791c0e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flow.run.cycle 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/skills/flow.run.cycle/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Run Cycle

Run FLOW work as a strict loop with CI-gated progression.

Contract

  • Use $flow-run for each individual task.
  • Process exactly one task cycle at a time.
  • Create or switch to the next task branch only after the previous task PR has all required CI checks passing.
  • Never pre-create branches for future tasks.
  • If CI fails, fix issues on the same branch, push, and re-run CI review until green.

Cycle Procedure

  1. Establish cycle state.
  • Inspect git status and current branch.
  • Check for an existing open FLOW task branch and PR.
  • If an in-flight task exists, resume from its CI state instead of starting a new branch.
  1. Verify previous task CI gate.
  • If there is an open PR for the previous task, run CI review (use gh-pr-results-review).
  • Treat the gate as open only when all required checks are successful.
  • If checks are pending, wait and re-check.
  • If checks fail, fix failures on that same task branch and repeat CI review.
  1. Start next task only after gate is open.
  • Select the next task from the workplan.
  • Create the new task branch only now.
  • Execute the full single-task FLOW using $flow-run end-to-end.
  1. Close the cycle iteration.
  • Confirm the new PR exists for the task completed in this iteration.
  • Run CI review for that PR.
  • Do not move to another task until this PR is green.
  1. Continue or stop.
  • Continue looping only if the user asked for multiple tasks or continuous mode.
  • Stop when requested, when no ready tasks remain, or when blocked by external dependencies.

Required Behaviors

  • Keep task boundaries strict: no mixed commits across tasks.
  • Preserve FLOW artifact expectations under SPECS/INPROGRESS/ and SPECS/ARCHIVE/.
  • Report cycle status after each iteration: task ID, PR link/number, CI state, and whether next-branch creation is allowed.
  • When blocked, report the blocker and exact unblock condition.

Trigger Phrases

Use this skill when requests look like:

  • "Run FLOW in a cycle for next tasks."
  • "Keep doing tasks one by one, only after CI passes."
  • "Automate sequential FLOW delivery with CI gating between tasks."
  • "Do the next tasks continuously but never start a new branch before previous checks are green."

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 59 lines · 66 tokens per session scan A fd3b791c0e69

Subscribe to this mod's changes

flow.run.cycle is a skill published in the GitHub repository SoundBlaster/XcodeMCPWrapper (20 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 571 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 2026-08-30.

Related

Other skills, from other repositories

stale-sweep

Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…

googleapis/mcp-toolbox · 159 tokens

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens

github-issue-triage

Issue triage and lifecycle management agent for ZeroClaw. Use this skill whenever the user wants to: triage open issues, close stale/duplicate/fixed issues, apply labels, run a backlog sweep, enforce the current issue stale policy, or handle a specific issue. Trigger on: 'triage issues', 'issue triage', 'sweep…

zeroclaw-labs/zeroclaw · 140 tokens

trello

Manages Trello boards, lists, and cards via the Trello REST API. Use when the user wants to create cards, move tasks between lists, list boards, add comments, archive cards, or check what is on a Trello board. Handles authentication, pagination, and rate-limit awareness for all Trello REST endpoints.

elizaOS/eliza · 69 tokens

copilotkit-contribute

Use when contributing to the CopilotKit open-source project — forking, cloning, setting up the monorepo, creating branches, running tests, and submitting pull requests against CopilotKit/CopilotKit.

CopilotKit/CopilotKit · 49 tokens

triage

Triage open herdr GitHub issues into a concise decision-first Markdown table. Use when the user says "triage", asks to triage open issues, asks which issues need attention, or wants issue priority/recommendation lights for herdr.

herdrdev/herdr · 53 tokens