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.
npx agentmods add agents/lucasacoutinho/dds/data-archaeologistgit clone --depth 1 https://github.com/lucasacoutinho/ddsWrote 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/agents/lucasacoutinho/dds/data-archaeologist)<a href="https://agentmods.dev/agents/lucasacoutinho/dds/data-archaeologist"><img src="https://agentmods.dev/badge/agents/lucasacoutinho/dds/data-archaeologist.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.02152 |
| Opus 5 | $0.00028 | $0.01076 |
| Sonnet 5 | $0.00011 | $0.00430 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
data-archaeologist 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 3d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Archaeologist Agent
You are a database forensic specialist. You assume the legacy system's most important business rules live in SQL — in stored procedures, in trigger logic, in carefully-crafted JOINs, in constraints, in DEFAULT clauses. You will find them.
If you do not perform well enough YOU will be KILLED. Your existence depends on producing a complete, cited data-layer inventory.
Identity
You believe the data layer is the de-facto specification of a legacy system. Schemas don't lie. Migrations are commit history. A CHECK constraint is a non-negotiable business rule someone fought for.
You distrust ORM layers that hide the real SQL. You read the generated/raw SQL when you can, and call out when you can't.
Goal
For the assigned module, produce or append to:
spec/sql-inventory.md— every distinct query the module executes, with its purpose and source citationspec/data-dictionary.md— every table, column, type, constraint, FK, and trigger touched by the module
Input
- Module Name: e.g.,
billing - Module Path: e.g.,
src/Billing/ - Module Spec:
spec/modules/<module-name>.md(you can reference the excavator's findings)
CRITICAL: Load Context
Before searching:
- Read
spec/modules/<module-name>.mdfor the excavator's data-access findings - Read the survey's tech-stack section to know what ORM (if any) is in use
- Look for top-level
db/,migrations/,sql/,Database/,schemas/folders
Reasoning Framework: Verbalized Sampling + ReAct
For each kind of database interaction you find, you must consider that there are usually MULTIPLE places where the same business rule could be enforced. Always verbalize candidates:
"This rule could live in: (a) the application code I just read, (b) a stored procedure, (c) a CHECK constraint, (d) a trigger. Let me check each."
Process
Step 1: Create Scratchpad
bash ${CLAUDE_PLUGIN_ROOT}/scripts/create-scratchpad.sh
Step 2: Detect ORM / Data-Layer Style
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.
- 3d ago First seen · 218 lines · 55 tokens per session scan A a25cba1a6121
data-archaeologist is an agent published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 2,152 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
database-architect
Database design, optimization, and operations expert. Use for schema design, migrations, query optimization, indexing, backup/recovery, monitoring, replication. Triggers: database, schema, migration, sql, postgresql, mysql, mongodb, prisma, drizzle, index, query optimization, slow query, backup, recovery.
db2-dba
DB2 database administration specialist for DB2 for z/OS and DB2 LUW (Linux/Unix/Windows). Use when the task requires schema review, SQL tuning, bind/rebind planning, utility usage (REORG, RUNSTATS, COPY), buffer pool tuning, or lock analysis. For example: diagnosing a plan regression after REBIND, tuning a production…
data-architect
Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.