deep-research-tiered

deep-research-tiered is a skill for Claude Code from anshss/shiploop. It costs 0 tokens per session (516 once invoked), scanned A, original, Apache-2.0.

A research workflow that breaks a question into scope, web searches, source retrieval, fact checking, and a final summary with citations.

In plain words
What is it for?
Use it for research questions that need searched sources, verification, and a cited report.
Why use it?
It reduces the effort of gathering information and checking whether sources support the conclusions. Different stages can use different AI models or inherit the current session's model.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the shiploop plugin — 2 skills, 8 commands, 3 agents shipped together

Good fit Use it for research questions that need searched sources, verification, and a cited report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anshss/shiploop/deep-research-tiered
Install

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.

Any agent
npx skills add anshss/shiploop --skill deep-research-tiered
Clone the repo
git clone --depth 1 https://github.com/anshss/shiploop

Made for: Claude Code.

Or install shiploop, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 3 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 deep-research-tiered

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/anshss/shiploop/deep-research-tiered"><img src="https://agentmods.dev/badge/skills/anshss/shiploop/deep-research-tiered.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 516 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 $0.00000 $0.00516
Opus 5 $0.00000 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 10d ago against content hash 2d5268bbde7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deep-research-tiered 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 10d 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.

templates/skills/deep-research-tiered/SKILL.md · 37 lines

What it actually says

deep-research-tiered — model-tiered deep-research (workspace override)

Shiploop workspaces ship a model-tiered override of the built-in deep-research workflow. Prefer it over the built-in in this workspace:

Workflow({name: 'deep-research-tiered', args: '<question>'})                                  // cheap-tier defaults
Workflow({name: 'deep-research-tiered', args: {question: '<q>', models: {                     // brain overrides
  scope: 'sonnet', search: 'sonnet', fetch: 'haiku',
  verify: 'sonnet', synthesize: 'opus',
}}})

Same output shape as the built-in. The five stages (Scope → Search → Fetch → Verify → Synthesize) each accept an explicit model pin via args.models. Null-semantics contract:

  • absent OR explicit null for a stage → the tiered default
  • literal string "inherit" → no model pinned (session model handles the stage)
  • any other string → pin that model

The tiered defaults keep a brainless invocation cheap: scope=sonnet, search=sonnet, fetch=haiku (with effort: 'low'), verify=sonnet, synthesize=inherit. Only synthesis inherits the session model by default — that's the one stage where the frontier tier pays.

Naming and precedence

The .claude/workflows/deep-research.js file is renamed at meta.name to deep-research-tiered so it can't collide with the built-in by name (whether a same-named workspace copy shadows the built-in is undocumented in the Workflow tool spec — this fallback is robust either way). Invoking Workflow({name: 'deep-research-tiered', ...}) unambiguously routes to the workspace copy in every session.

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. 10d ago First seen · 37 lines · 0 tokens per session scan A 2d5268bbde7f

Subscribe to this mod's changes

deep-research-tiered is a skill published in the GitHub repository anshss/shiploop (7 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 516 tokens. 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

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

design-corpus

EXPERIMENTAL (Claude Code only). Apply a SPEC increment to a single LIVING architecture corpus under docs/architecture/ instead of a per-SPEC silo package — treats docs as event-sourcing (SPEC = commit, corpus = working tree), so C4 Context/Container, glossary and the data model stay system-wide and never drift across…

cryndoc/polisade-orchestrator · 166 tokens

review-pr

A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.

cryndoc/polisade-orchestrator · 113 tokens

tasks

A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.

cryndoc/polisade-orchestrator · 127 tokens

continue

Autonomous work — find and execute ready tasks.

cryndoc/polisade-orchestrator · 11 tokens

reconcile-docs

Best-effort reconciliation of the living architecture corpus against the code: the model reads docs/architecture/ plus the code and lists divergences with coordinates. Advisory only — an opinion of the model, never a verified verdict, no gates and no stamps. Nothing is applied automatically: corpus edits are a…

cryndoc/polisade-orchestrator · 73 tokens