dogma: Skill for Claude Code

.github/skills/deep-research-sprint/SKILL.md

deep-research-sprint is a skill for Claude Code from EndogenAI/dogma. It costs 118 tokens per session (4,699 once invoked), scanned A, original, Apache-2.0.

A guided workflow for carrying out a formal research sprint from source collection through synthesis, review, archiving, and a final document. It uses a team of research agents and produces Markdown research files.

In plain words
What is it for?
Use it to start research topics, warm a local source cache, coordinate scouts and reviewers, and create finalized documents in the project’s research folder.
Why use it?
It provides a repeatable process for gathering evidence, combining findings, checking the result, and recording the work.

Skill for Claude Code

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

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dogma configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/fetch_all_sources.py --dry-run.

Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/skills/deep-research-sprint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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 deep-research-sprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/endogenai/dogma/deep-research-sprint/github.svg)](https://agentmods.dev/skills/endogenai/dogma/deep-research-sprint)
Your own site
<a href="https://agentmods.dev/skills/endogenai/dogma/deep-research-sprint"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/deep-research-sprint/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 deep-research-sprint

Your own site · 80×15
<a href="https://agentmods.dev/skills/endogenai/dogma/deep-research-sprint"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/deep-research-sprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,699 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 $0.00118 $0.04699
Opus 5 $0.00059 $0.02350
Sonnet 5 $0.00024 $0.00940
Haiku 4.5 $0.00012 $0.00470

Measured 9d ago against content hash 44d52c01f972, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-research-sprint 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 9d 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.

.github/skills/deep-research-sprint/SKILL.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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/.

Read the full file on GitHub · 401 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. 9d ago First seen · 401 lines · 118 tokens per session scan A 44d52c01f972

Subscribe to this mod's changes

deep-research-sprint is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 118 tokens to every session and 4,699 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

air-blackbox-sales-agent

AIR Blackbox's autonomous sales prospecting agent. Finds Python AI projects on GitHub that need EU AI Act compliance, identifies the right person to contact (CEO, CTO, lead maintainer), runs a free compliance scan, and drafts personalized outreach emails that convert to engagement. The sales flow: free scan as the…

airblackbox/airblackbox · 248 tokens

interpret-results

Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.

airblackbox/airblackbox · 49 tokens

compliance-scan

Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.

airblackbox/airblackbox · 51 tokens

nio-scan

Nio code/skill execution-risk scanner. Use when the user wants to scan a file, repo, directory, or skill for execution risks — e.g. "scan this code for risks", "is this file/plugin dangerous", "check this repo for malicious code", "run nio scan on ". Focused single-purpose skill; for other Nio operations use /nio.

core0-io/nio · 81 tokens

nio-external-score

Nio external scoring-endpoint snapshot. Use when the user asks about their current Nio/risk scores from configured external scoring endpoints — e.g. "what's my Nio score", "tell me the nio score", "check my external/guardrail endpoint scores", "what do my scoring services return right now", "list the current risk…

core0-io/nio · 97 tokens

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

synthetic-sciences/openscience · 58 tokens