dogma: Skill for Claude Code

Deep Research Sprint

This skill enacts the Endogenous-First axiom from MANIFESTO.md by encoding the complete research sprint workflow as a reusable procedure. The full orchestration pattern is governed by AGENTS.md and the executive fleet design in .github/agents/README.md. Read AGENTS.md before modifying any step in this pipeline.

---

Core Principle: Every research sprint includes mandatory web scouting to discover and validate external authoritative sources. Endogenous-First means you consult local corpus and cache first, but web searching is the primary expansion activity — it is never optional and should never be skipped to save time or tokens.

---

1. Pre-Flight: Fetch-Before-Act

Before delegating to any scout, warm the source cache. This implements the Algorithms Before Tokens axiom: scouts read cached Markdown files with read_file rather than re-fetching pages through the context window.

# Preview what will be fetched (safe dry run — always do this first)
uv run python scripts/fetch_all_sources.py --dry-run

# Fetch all uncached sources (idempotent — skips already-cached URLs)
uv run python scripts/fetch_all_sources.py

Check before fetching any individual URL: use --check to see if a page is already cached:

uv run python scripts/fetch_source.py <url> --check

Re-fetching a cached source wastes tokens. If .cache/sources/ already has the page, read it directly.

Source Cache vs. Committed Source Stubs

Location	Purpose	Committed?
.cache/sources/	Fetched page content (Markdown)	No — gitignored
docs/research/sources/	Source stub files referenced from research docs	Yes — committed

This distinction is critical for CI: research docs that link to docs/research/sources/ expect committed stub files. Stub files in .cache/sources/ exist only locally and will cause lychee "Cannot find file" errors in CI. When a source is cited in a committed research doc, create a stub in docs/research/sources/ even if the full content is only in .cache/sources/.