Agent skill

Sesh Config Schema Sync Check

by joshmedeski in joshmedeski/sesh

Checks that every TOML field added, renamed or removed in Go code has a matching update in sesh's JSON schema, so TOML editors don't reject valid config with a schema error.

MITAuto-check passedDevelopment

Install Sesh Config Schema Sync Check

skills CLI
$ npx skills add joshmedeski/sesh --skill config-schema-sync -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install joshmedeski/sesh config-schema-sync --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/joshmedeski/sesh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/config-schema-sync .claude/skills/config-schema-sync && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
config-schema-sync
GitHub stars
2.9k
Token cost
~731 tokens
SKILL.md length
262 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Checks that every TOML field added, renamed or removed in Go code has a matching update in sesh's JSON schema, so TOML editors don't reject valid config with a schema error.

  • Works in 4 steps: List the TOML fields… → For every changed field, verify… → Report discrepancies. For each field… → …
  • Reviewing a diff that adds or renames a field in sesh's Go config struct
  • SKILL.md covers When to run this check, Procedure, Quick diff-check one-liner and Do not
  • Calls rg and git

What it does

The skill triggers whenever a diff touches model/config.go, a Go struct tagged with a toml field name, or files under configurator/, since any field that exists in the Go model but is missing from sesh.schema.json produces an additional-properties error for users editing their config in an editor that loads the schema through its #:schema directive.

It lists the TOML fields added, renamed or removed in the diff with a targeted git diff and ripgrep command, then maps each affected Go struct to its location in the schema, for example Config to the top-level properties and SessionConfig to properties.session.items.properties, and checks each changed field name against the schema file directly. Any field present in Go but missing or stale in the schema is either added with an appropriate type, description and default, or flagged in the review for the author to decide, while existing schema conventions such as additionalProperties: false on nested objects and a description that mirrors the field's purpose are preserved.

When your agent uses it

  • Reviewing a diff that adds or renames a field in sesh's Go config struct
  • Checking why a sesh TOML config file is rejected by an editor's schema validation
  • Keeping sesh.schema.json in sync after a configurator change

Example prompts

  • “Check whether this diff to model/config.go needs a schema update.”
  • “Why does my sesh.toml get an additional-properties error in my editor?”
  • “Sync sesh.schema.json after renaming the WindowConfig fields.”

Requirements

  • git and ripgrep

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. List the TOML fields added/renamed/removed in the diff
  2. For every changed field, verify sesh.schema.json matches. Map the Go struct to its schema location
  3. Report discrepancies. For each field present in Go but missing (or stale) in the schema, either
  4. Preserve schema conventions when editing

What it can do on your machine

Read from SKILL.md and the folder at commit 59b8478. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sesh Config Schema Sync Check loads about 731 tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~731

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from joshmedeski/sesh at commit 59b8478, republished under its MIT licence (© joshmedeski). 262 words, ~731 tokens.

Download SKILL.mdSave it as .claude/skills/config-schema-sync/SKILL.md (or your agent's skills folder).
name
config-schema-sync
description
Use when reviewing, writing, or committing changes that touch model/config.go or any TOML config struct in this repo. Verifies that every added, renamed, or removed TOML field has a matching update in sesh.schema.json so the JSON schema used by TOML editors (via `#:schema` directive) stays in sync with the Go config model. Trigger whenever a diff touches files under model/, configurator/, or any struct tagged with `toml:"..."`.
metadata.internal
true

Config ↔ Schema Sync Check

The sesh.schema.json file at the repo root is the public JSON Schema that TOML editors load via #:schema https://github.com/joshmedeski/sesh/raw/main/sesh.schema.json. Any config field that exists in Go but is missing from the schema produces "Additional properties are not allowed" errors for users (see issue #367 for precedent).

When to run this check

Run whenever a change touches any of:

  • model/config.go
  • Any Go struct with toml:"..." tags
  • Files under configurator/

Procedure

  1. List the TOML fields added/renamed/removed in the diff:

    bash
    git diff --unified=0 -- model/config.go configurator/ | rg 'toml:"[^"]+"'
  2. For every changed field, verify sesh.schema.json matches. Map the Go struct to its schema location:

    Go structSchema path
    Configtop-level properties
    DefaultSessionConfigproperties.default_session.properties
    SessionConfigproperties.session.items.properties
    WindowConfigproperties.window.items.properties
    WildcardConfigproperties.wildcard.items.properties

    Check each changed field:

    bash
    rg '"<field_name>"' sesh.schema.json
  3. Report discrepancies. For each field present in Go but missing (or stale) in the schema, either:

    • Add it to the schema with an appropriate type, description, and default where applicable, or
    • Flag it in the review output so the author can decide.
  4. Preserve schema conventions when editing:

    • additionalProperties: false on nested objects — keep it.
    • description is required and should mirror the field's purpose (not just restate the name).
    • Include default when the Go zero-value is meaningful.
    • Use type: "string" | "boolean" | "integer" | "array" matching the Go type.

Quick diff-check one-liner

bash
# Extract TOML field names from Go, compare against schema
comm -23 \
  <(rg -o 'toml:"([^,"]+)' -r '$1' model/config.go | sort -u) \
  <(rg -o '"([a-z_]+)":\s*\{' -r '$1' sesh.schema.json | sort -u)

Any field printed is in Go but not in the schema — investigate.

Do not

  • Do not bump the schema $id URL.
  • Do not remove additionalProperties: false to "fix" a missing field — add the field instead.
  • Do not add fields to the schema that are not yet merged in Go; the schema should track main.

© joshmedeski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/config-schema-sync of joshmedeski/sesh.

Open the folder on GitHubat commit 59b8478

Compare with similar skills

Sesh Config Schema Sync Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sesh Config Schema Sync Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sesh Config Schema Sync Check this skilljoshmedeski/sesh2.9k—~731Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from joshmedeski/sesh

  • Sesh Terminal Sessions

    joshmedeski/sesh

    Starts work in tmux sessions and windows through sesh instead of raw tmux commands, resolving names, directories, zoxide results and configured sessions.

    2.9k GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Sesh Config Schema Sync Check

What does Sesh Config Schema Sync Check do?

Checks that every TOML field added, renamed or removed in Go code has a matching update in sesh's JSON schema, so TOML editors don't reject valid config with a schema error. json produces an additional-properties error for users editing their config in an editor that loads the schema through its #:schema directive.

When should I use Sesh Config Schema Sync Check?

Sesh Config Schema Sync Check fits situations like: reviewing a diff that adds or renames a field in sesh's Go config struct; checking why a sesh TOML config file is rejected by an editor's schema validation; keeping sesh.schema.json in sync after a configurator change.

How do I install Sesh Config Schema Sync Check in Claude Code?

Run `npx skills add joshmedeski/sesh --skill config-schema-sync -a claude-code`. Or copy the skill folder (.claude/skills/config-schema-sync in joshmedeski/sesh) into .claude/skills/config-schema-sync in your project. Claude Code loads it when a task matches its description.

How do I install Sesh Config Schema Sync Check in Codex?

Run `npx skills add joshmedeski/sesh --skill config-schema-sync -a codex`. Or copy the skill folder (.claude/skills/config-schema-sync in joshmedeski/sesh) into .agents/skills/config-schema-sync in your project. Codex loads it when a task matches its description.

Can I use Sesh Config Schema Sync Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joshmedeski/sesh --skill config-schema-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/config-schema-sync, .gemini/skills/config-schema-sync, .github/skills/config-schema-sync and .opencode/skills/config-schema-sync in your project.

What does Sesh Config Schema Sync Check need to run?

Going by SKILL.md and its folder, Sesh Config Schema Sync Check needs the command-line tools its instructions call (rg and git). Our summary lists: git and ripgrep.

Does Sesh Config Schema Sync Check access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Sesh Config Schema Sync Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sesh Config Schema Sync Check use?

Sesh Config Schema Sync Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sesh Config Schema Sync Check use?

About 731 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sesh Config Schema Sync Check?

Skills that share tags, products or a category with Sesh Config Schema Sync Check: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sesh Config Schema Sync Check?

joshmedeski (a GitHub user) maintains it in joshmedeski/sesh, which has 2,862 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 6, 2026.

Source: joshmedeski/sesh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.