synthesis-preflight

synthesis-preflight is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 82 tokens per session (1,678 once invoked), scanned A, original, Apache-2.0.

A checklist that decides whether a software branch is mechanically ready for a pull request, which is a proposed code change for review and merging. It checks branch state, tests, code, temporary workarounds, and commit history.

In plain words
What is it for?
Use it before creating a pull request to check the working tree, tests and types, branch hygiene, temporary changes, and commit quality.
Why use it?
It catches release-readiness problems that can remain even when the code appears to work, such as uncommitted files, broken tests, or unclear commits.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit Use it before creating a pull request to check the working tree, tests and types, branch hygiene, temporary changes, and commit quality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-preflight
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.

Any agent
npx skills add synthesisengineering/synthesis-skills --skill synthesis-preflight
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 hooks.

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 synthesis-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-preflight/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-preflight)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-preflight"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-preflight/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.

agentmods 80×15 button for synthesis-preflight

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-preflight"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00082 $0.01678
Opus 5 $0.00041 $0.00839
Sonnet 5 $0.00016 $0.00336
Haiku 4.5 $0.00008 $0.00168

Measured 10d ago against content hash 9cefba386dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

synthesis-preflight 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 10d 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.

skills/synthesis-preflight/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Preflight

Preflight is a branch readiness gate. It does not evaluate whether your code is correct — that is the job of synthesis-implementation-integrity (self-review) and synthesis-code-audit (quality scan). Preflight asks a different question: is this branch mechanically ready to become a PR?

A branch can contain perfectly good code and still fail preflight: tests broken, uncommitted changes left behind, vague commit messages, a stale workaround that should have been removed. Preflight catches the things that fall between "the code works" and "the branch is ready."


Where This Fits

Skill Scope When to use
implementation-integrity Self-verification of a single implementation After completing work — "Is my code genuinely complete?"
code-audit 10-dimension quality scan of a diff After implementation — systematic quality measurement
preflight (this one) Branch readiness gate Before creating a PR — "Is this branch ready?"

The natural flow: Implement → self-verify (implementation-integrity) → quality scan (code-audit) → branch gate (preflight) → create PR → peer review (pr-review).

Preflight assumes implementation-integrity was already run during development. It does not re-check whether the code is complete — it checks whether the branch is ready to leave your machine.


The Quality Gate Framework

Preflight evaluates six orthogonal dimensions. Each is graded independently:

  • Pass — no issues
  • Warning — potential concern, does not block
  • Fail — blocks the PR until resolved

A single FAIL in any dimension means the branch is NOT READY. The verdict is mechanical — no human override of FAIL dimensions. Warnings are surfaced for awareness but do not block.


Quality Dimensions

1. Branch Verification

  • Confirm you are on a feature, fix, or working branch — not on the default branch (main, master, or whatever the project designates as protected). Refuse to proceed if on a protected branch.
  • Count commits ahead of the base branch. If the branch is behind the base, warn that a sync may be needed before PR creation.

Read the full file on GitHub · 157 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. 10d ago First seen · 157 lines · 82 tokens per session scan A 9cefba386dd8

Subscribe to this mod's changes

synthesis-preflight is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,678 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 2026-08-30.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens