What is schema-sync-fully-guided?

A guided repair procedure for keeping four parts of the Ghost Contributors NL2SQL system in agreement: its data rules, search index, and two prompts. NL2SQL means turning plain-language questions into SQL database queries.

Use it to preview, apply, validate, or roll back schema changes such as renaming a column.

It helps repair schema drift, which happens when the database changes but related rules, search data, or prompts do not.

schema-sync-fully-guided — Skill by DSmmartin

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/DSmmartin/skills_talk_agent_camp_2026

agentmods

npx agentmods add skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided/github.svg)](https://agentmods.dev/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided)

Your own site

<a href="https://agentmods.dev/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided"><img src="https://agentmods.dev/badge/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided"><img src="https://agentmods.dev/badge/skills/dsmmartin/skills_talk_agent_camp_2026/03_fully_guided.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,068 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00065	$0.01068
Opus 5.5	$0.00026	$0.00427
Sonnet 5.5	$0.00013	$0.00214
Haiku 4.5	$0.00006	$0.00107

Measured 2mo ago against content hash a08e83cbe61b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

schema-sync-fully-guided 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.

dev_tools/skill_examples/03_fully_guided/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schema Sync — Fully Guided

Read dev_tools/README.md and dev_tools/skill_examples/03_fully_guided/references/schema-layers.md before starting. They contain field-level detail about what each layer holds and what to change.

One-command fix

If the migration matches the standard merged → merged_at rename pattern, the full procedure is automated:

# Preview what will change (nothing is written)
uv run python dev_tools/schema_sync.py --table github_events --dry-run

# Apply all four patches
uv run python dev_tools/schema_sync.py --table github_events

# Confirm no drift
uv run python scripts/validate_schema.py

A SchemaSyncReport is printed listing every change made across all four layers.

Step-by-step procedure (for non-standard migrations)

Use this when the one-command fix does not cover the migration, or when you need to apply patches selectively.

Pre-check — confirm drift exists

uv run python scripts/validate_schema.py

If "No drift" is reported, the system is already in sync. Stop here.

Step 1 — Introspect live ClickHouse schema

uv run python dev_tools/scripts/clickhouse_introspect.py --table github_events

Note every column that is new, removed, or type-changed compared to the YAML contract. See references/schema-layers.md for the expected post-migration schema.

Step 2 — Patch YAML contract

# Preview
uv run python dev_tools/scripts/yaml_patch.py --table github_events --dry-run

# Apply
uv run python dev_tools/scripts/yaml_patch.py --table github_events

If patching manually: edit agentic_system/schema/github_events.yaml.

Add the new column entry (name, type, description).
Update the description of any renamed or type-changed column to document post-migration semantics.
Do NOT remove columns that still exist in the DB (even if zeroed out).

Step 3 — Patch ChromaDB RAG chunks

# Preview
uv run python dev_tools/scripts/chroma_patch.py --dry-run

# Apply
uv run python dev_tools/scripts/chroma_patch.py

Read the full file on GitHub · 141 lines

Files

What ships with it

2 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.

2mo ago First seen · 141 lines · 65 tokens per session scan A a08e83cbe61b

Subscribe to this mod's changes

schema-sync-fully-guided is a skill published in the GitHub repository DSmmartin/skills_talk_agent_camp_2026 (9 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,068 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 2026-08-31.

Data and AI Databases RAG and vectors

schema-sync-fully-guided next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
schema-sync-fully-guidedDSmmartin/skills_talk_agent_camp_2026	Skill	9	6mo ago	Apache-2.0	A	65	Claude Code, Codex
chromaNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	12	Claude Code, Codex
embeddingsruvnet/ruflo	Skill	81k	yesterday	MIT	A	62	Claude Code
rag-pineconedavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	65	Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	3d ago	Apache-2.0	A	30	Claude Code, Codex
pgvector-semantic-searchtimescale/pg-aiguide	Skill	1.9k	3d ago	Apache-2.0	A	190	Cursor
postgres-hybrid-text-searchtimescale/pg-aiguide	Skill	1.9k	3d ago	Apache-2.0	A	162	Cursor