What is concept-research-navigation?

A navigation guide for concept research, including dossiers, source directories, extracted evidence, and image checks.

Use it when finding research data, verifying claims, extracting sources, checking images, or reviewing research directories.

It helps locate the right research files and review whether claims, sources, paraphrases, and images meet the expected quality.

How 1cFE/fusion-tea configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 1cFE/fusion-tea. 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/1cFE/fusion-tea/main/.claude/skills/concept-research-navigation/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/1cFE/fusion-tea

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/1cfe/fusion-tea/concept-research-navigation/github.svg)](https://agentmods.dev/skills/1cfe/fusion-tea/concept-research-navigation)

Your own site

<a href="https://agentmods.dev/skills/1cfe/fusion-tea/concept-research-navigation"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/concept-research-navigation/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/1cfe/fusion-tea/concept-research-navigation"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/concept-research-navigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,303 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.

Model	Per session	Once invoked
Fable 5.1	$0.00111	$0.01303
Opus 5.5	$0.00044	$0.00521
Sonnet 5.5	$0.00022	$0.00261
Haiku 4.5	$0.00011	$0.00130

Measured 2mo ago against content hash e1cf5306346a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

concept-research-navigation 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 2mo 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.

.claude/skills/concept-research-navigation/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Methodology for finding, evaluating, and using concept research data in knowledge/concept_research/.

Core Principle

Research data is evidence, not truth. Every source has a quality tier and an extraction method. Dossiers synthesize across sources but are not authoritative for specific claims. Individual sources are authoritative for what they contain, but text extraction is lossy — images may hold data the text doesn't. Always trace quantitative claims to the most authoritative representation available.

Data Layout (Brief)

For full directory structure, R2 sync setup, and format details, see knowledge/concept_research/README.md. Minimal orientation:

Concept directories: knowledge/concept_research/{concept-id}/ (e.g., 11-magnetic-mirror/)
Start with {concept-id}/dossier.md for synthesized overview
Evidence in {concept-id}/iter-NN/sources/*.md — check ALL iterations

Source Discovery Protocol

To find research for a given concept:

If you know the concept ID: go to knowledge/concept_research/{concept-id}/
If you don't: check knowledge/concept_research/SOURCE_INDEX.md, or glob knowledge/concept_research/*/dossier.md
Read dossier.md for orientation — what the concept is, key parameters, which sources exist
Find evidence in iter-NN/sources/*.md — check ALL iterations, later ones may add new sources
For each source, check if companion directory iter-NN/sources/{name}/ exists. Its presence indicates richer data: images, original artifacts (raw.html/raw.pdf), and extraction metrics

Source Evaluation

Three quality tiers. How to identify and how much to trust:

Tier	How to identify	Trust level
Direct extraction	YAML frontmatter with `source:`, `backend:`, `content_hash_sha256:`	Authoritative for what it contains. Text may be lossy — verify quantitative data against images.
Haiku paraphrase	No YAML frontmatter, starts with `# Title` directly (or is a `.orig.md` file)	Lossy summary by Haiku. Specific numbers and technical details may be wrong. Flag as unverified if citing values.
Dossier	`dossier.md` at concept root	Synthesized overview. Good for orientation. Do NOT treat as authoritative for specific numbers — trace claims to individual sources.

Read the full file on GitHub · 100 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.

2mo ago First seen · 100 lines · 111 tokens per session scan A e1cf5306346a

Subscribe to this mod's changes

concept-research-navigation is a skill published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 111 tokens to every session and 1,303 once invoked, about $0.0004 per session on Opus 5.5. 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.

Research

concept-research-navigation next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
concept-research-navigation1cFE/fusion-tea	Skill	5	24d ago	MIT	A	111	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

fusion-tea: Skill for Claude Code