synthesis-repo-guard

synthesis-repo-guard is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 48 tokens per session (4,626 once invoked), scanned B, original, Apache-2.0.

A guard for keeping track of unsynced changes in Git repositories, which store versions of code and files. It records local handoff information and groups private project-context commits for an explicit remote handoff or end-of-day checkpoint.

In plain words
What is it for?
Use it to detect repositories with unsynced work, record which session produced local handoff state, and prepare private context changes for an intentional remote sync.
Why use it?
Coding tools and manual work can leave changes only on one computer. This helps recover local work while keeping the decision to publish changes to a remote repository deliberate and avoiding confidential details in alerts.

Skill for Claude CodeCodex

Written for Claude Code and Codex: PostToolUse hook event, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

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

Good fit Use it to detect repositories with unsynced work, record which session produced local handoff state, and prepare private context changes for an intentional remote sync.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-repo-guard"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-repo-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00048 $0.04626
Opus 5 $0.00024 $0.02313
Sonnet 5 $0.00010 $0.00925
Haiku 4.5 $0.00005 $0.00463

Measured today against content hash 69a3124ac292, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

synthesis-repo-guard scanned grade B with 1 finding 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 today.

The scan reads SKILL.md. This mod also ships 4 executable files (checkpoint_sync.py, repo_sync_check.py, test_checkpoint_sync.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

### Claude Code (`~/.claude/settings.json`)
skills/synthesis-repo-guard/SKILL.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Repo Guard

The Problem

AI coding assistants and project-management tooling create and modify files continuously. A stopped task needs lightweight same-machine recovery immediately, while another computer needs a deliberate publication boundary. Treating both cases as an automatic commit creates noisy history and network latency; treating neither creates invisible local-only state. Tools that write files outside agent sessions (a project console writing status markers, manual edits) need the same attribution contract.

v1 of this skill detected stranded state and alerted with a count ("N repositories have unsynced changes"). Two failures emerged in practice:

  1. The alert was unactionable — and leaky if made actionable. A count says nothing useful; speaking repo names would fix that, but repo/workspace names are often client names, and audio reaches whoever is nearby or on an unmuted call. Notification banners leak the same way during screen-shares.
  2. The alert fired on machine-fixable states. Most unsynced state is exactly what automation should heal at the next sensible checkpoint. Alerting humans about machine-fixable problems trains them to ignore alerts.

The Architecture — three layers

Layer Component Job
Detector repo_sync_check.py (scan) Find dirty / ahead / behind / detached repos under a workspace root
Messenger repo_sync_check.py (output) Generic audio/banner ping + detailed report files + console tile data
Checkpointer checkpoint_sync.py Record local handoffs; batch exact context paths at explicit remote-sync events

End state: same-computer client switching is filesystem-local and fast. Cross-computer publication is batched and explicit. The synthesis-console shows ambient status, and alerts remain rare and actionable.

Confidentiality rule for alert surfaces (ABSOLUTE)

Audio (say, alert sounds) and macOS notification banners never carry repo names, workspace names, or client names — only counts and a pointer ("details are in your synthesis console"). This holds at all times, not only while screen-sharing: presence detection is unreliable, and one leak outweighs the convenience. Identifying detail belongs exclusively in pull channels the user deliberately opens:

Read the full file on GitHub · 357 lines

Files

What ships with it

6 files 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. today Changed · +62 lines 69a3124ac292
  2. 2d ago Changed · +9 lines b8f1a9c81147
  3. 6d ago Changed · +4 lines 86a96652a2ba
  4. 8d ago Changed · +7 lines ce5925e7fc0b
  5. 12d ago First seen · 275 lines · 48 tokens per session scan B d5259de42d1e

Subscribe to this mod's changes

synthesis-repo-guard is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 4,626 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.