Borrowing it
Nothing to install: this file belongs to SoundBlaster/XcodeMCPWrapper. 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/SoundBlaster/XcodeMCPWrapper/main/.agents/skills/flow-run/SKILL.mdgit clone --depth 1 https://github.com/SoundBlaster/XcodeMCPWrapperWrote 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/soundblaster/xcodemcpwrapper/flow-run)<a href="https://agentmods.dev/skills/soundblaster/xcodemcpwrapper/flow-run"><img src="https://agentmods.dev/badge/skills/soundblaster/xcodemcpwrapper/flow-run/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/skills/soundblaster/xcodemcpwrapper/flow-run"><img src="https://agentmods.dev/badge/skills/soundblaster/xcodemcpwrapper/flow-run.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 | $0.00070 | $0.01421 |
| Opus 5.5 | $0.00028 | $0.00568 |
| Sonnet 5.5 | $0.00014 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
flow-run 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 2mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Run
Execute the workflow in SPECS/COMMANDS/FLOW.md exactly, without skipping required steps unless the workflow itself explicitly allows skipping.
Required Inputs
Collect these before starting:
- Task identifier (for example
P5-T2) and short description. - Current branch and whether a feature branch already exists.
- Confirmation of which review subject name to use for
REVIEW_{subject}.md.
If the task identifier is unknown, determine it from SPECS/Workplan.md and SPECS/INPROGRESS/next.md during SELECT.
Execution Contract
Apply these rules throughout execution:
- Read
SPECS/COMMANDS/FLOW.mdat the beginning and treat it as the source of truth. - Complete steps in order:
BRANCH -> SELECT -> PLAN -> EXECUTE -> ARCHIVE -> REVIEW -> FOLLOW-UP -> ARCHIVE-REVIEW -> PR -> CI-REVIEW. - Use the
flow-primitive-commitskill for every commit checkpoint — stage only task-relevant files and use present-tense FLOW message patterns. - Run required quality gates during EXECUTE (
pytest,ruff check src/,mypy src/if configured,pytest --covwith coverage >= 90%). - Record artifacts in expected locations under
SPECS/INPROGRESS/andSPECS/ARCHIVE/. - If REVIEW has no actionable issues, skip FOLLOW-UP and proceed directly to ARCHIVE-REVIEW, as FLOW permits.
- After ARCHIVE-REVIEW, use the
gh-create-prskill to open a pull request from the feature branch intomain.
Step Procedure
- BRANCH
- Ensure
mainis up to date. - Create
feature/{TASK_ID}-{short-description}if not already on the correct feature branch. - Use
flow-primitive-commitskill — commit message pattern:Branch for {TASK_ID}: {short description}.
- SELECT
- Choose the next task from
SPECS/Workplan.md(optionally withpython scripts/pick_next_task.py). - Update
SPECS/INPROGRESS/next.mdwith selected task metadata. - Use
flow-primitive-commitskill — commit message pattern:Select task {TASK_ID}: {TASK_NAME}.
- PLAN
- Create the task PRD at
SPECS/INPROGRESS/{TASK_ID}_{TASK_NAME}.md. - Define deliverables, acceptance criteria, dependencies.
- Use
flow-primitive-commitskill — commit message pattern:Plan task {TASK_ID}: {TASK_NAME}.
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.
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.
- 2mo ago First seen · 104 lines · 70 tokens per session scan A a7cb6342ec54
flow-run is a skill published in the GitHub repository SoundBlaster/XcodeMCPWrapper (20 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,421 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pr-hygiene
Check a pull request is small, described, tested, and free of secrets before opening or reviewing it. Use when drafting a PR, reviewing a diff, or verifying a change is ready to share.
commit-message
Write a conventional, imperative git commit message from the staged diff. Use when committing, amending, or rewriting a commit message.
changelog-notes
Draft user-facing changelog bullets from a diff or merged PR. Use when writing release notes, CHANGELOG entries, or a PR summary for humans.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.