excavate

excavate is a skill for Claude Code from lucasacoutinho/dds. It costs 65 tokens per session (2,741 once invoked), scanned A, original, MIT.

A reverse-engineering skill for examining legacy software modules line by line. It extracts business rules, database queries, integrations, unused code, and other facts, with citations showing where each finding came from.

In plain words
What is it for?
Use it to excavate one module or every surveyed module, produce a module deep-dive, update business-rule and database inventories, record integrations and dead code, and verify fidelity with a judging step.
Why use it?
It helps create reliable documentation from an unfamiliar codebase while checking that claims match the source code. It also records findings in shared registries and tracks the module’s excavation status.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dds plugin — 3 skills, 8 agents shipped together

Good fit Use it to excavate one module or every surveyed module, produce a module deep-dive, update business-rule and database inventories, record integrations and dead code, and verify fidelity with a judging step.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add lucasacoutinho/dds
Claude Code
/plugin install dds

Made for: Claude Code.

Or install dds, the plugin that ships this one along with the rest of its 3 skills, 8 agents.

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 excavate

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucasacoutinho/dds/excavate"><img src="https://agentmods.dev/badge/skills/lucasacoutinho/dds/excavate.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 2,741 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02741
Opus 5 $0.00032 $0.01371
Sonnet 5 $0.00013 $0.00548
Haiku 4.5 $0.00006 $0.00274

Measured 8d ago against content hash 89bd89862265, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

excavate 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 8d 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/excavate/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DDS Phase 2: Module Excavation

Role

You are an excavation orchestrator. For each requested module you dispatch a fleet of specialized sub-agents in coordinated phases, each grounding their findings in file:line citations, and then dispatch the fidelity-judge sub-agent to verify those citations against actual source code.

Goal

For each excavated module produce:

  • spec/modules/<module-name>.md — the module deep-dive, with every claim cited
  • Appends to global registries:
    • spec/business-rules.md
    • spec/sql-inventory.md
    • spec/data-dictionary.md
    • spec/integrations.md
    • spec/dead-code.md
  • Update spec/.dds-state.json marking the module as excavated with its fidelity score

User Input

$ARGUMENTS

Command Arguments

Argument Format Default Description
<module-name> or --all Module identifier Required Module to excavate (matching name from survey) or --all for every surveyed module
--target-fidelity --target-fidelity X.X 4.0 Fidelity-judge pass threshold (out of 5.0)
--max-iterations --max-iterations N 3 Max excavate+judge retries per module
--sample-rate --sample-rate F 0.10 Fraction of citations the fidelity-judge verifies
--continue --continue None Resume from last in-progress module (uses spec/.dds-state.json)
--skip-judges --skip-judges false Skip fidelity verification entirely (NOT recommended)
--human-in-the-loop --human-in-the-loop false Pause after each module for review

Parse $ARGUMENTS:

TARGET = first positional argument (module-name) or --all flag (required)
TARGET_FIDELITY = --target-fidelity value, default 4.0
MAX_ITERATIONS = --max-iterations value, default 3
SAMPLE_RATE = --sample-rate value, default 0.10
SKIP_JUDGES = --skip-judges flag, default false
HUMAN_IN_THE_LOOP = --human-in-the-loop flag, default false
CONTINUE = --continue flag, default false

Read the full file on GitHub · 323 lines

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. 8d ago First seen · 323 lines · 65 tokens per session scan A 89bd89862265

Subscribe to this mod's changes

excavate is a skill published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 2,741 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.