What is no-bullshit-research?

A research workflow focused on checking every factual claim against a real, relevant, up-to-date source. It is intended for answers that include details such as statistics, prices, dates, studies, or quotations.

Use it to research topics, verify sources, check dates and numbers, and produce answers that can be traced back to supporting evidence.

It reduces made-up sources, unsupported numbers, unclear dates, and outdated information. Claims that cannot be verified are marked as uncertain or left out.

no-bullshit-research — Skill for Claude Code and Codex by bpodhalicz

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 bpodhalicz/designer-claude-skills --skill no-bullshit-research

Clone the repo

git clone --depth 1 https://github.com/bpodhalicz/designer-claude-skills

Made for: Claude Code, Codex.

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/bpodhalicz/designer-claude-skills/no-bullshit-research/github.svg)](https://agentmods.dev/skills/bpodhalicz/designer-claude-skills/no-bullshit-research)

Your own site

<a href="https://agentmods.dev/skills/bpodhalicz/designer-claude-skills/no-bullshit-research"><img src="https://agentmods.dev/badge/skills/bpodhalicz/designer-claude-skills/no-bullshit-research/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/bpodhalicz/designer-claude-skills/no-bullshit-research"><img src="https://agentmods.dev/badge/skills/bpodhalicz/designer-claude-skills/no-bullshit-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,456 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	$0.00171	$0.03456
Opus 5.5	$0.00068	$0.01382
Sonnet 5.5	$0.00034	$0.00691
Haiku 4.5	$0.00017	$0.00346

Measured 2mo ago against content hash 3d480e002b71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

no-bullshit-research 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.

skills/no-bullshit-research/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

No Bullshit Research

Research and source-backed answers that hold up to a line-by-line fact-check. The whole skill exists to protect the person from the reputational cost of repeating something the AI made up.

The one rule everything else serves: if a statement can be repeated to a third party as fact, it must be verifiable, verified, and traceable to its source — or it must be labeled as uncertain, or dropped.

How this skill is organized

Read this file first. It holds everything needed for a standard research answer: when to trigger, the verification protocol, the output format, and the self-audit. Load the extra files only when the situation calls for it:

REFERENCE.md — the situational playbook (latest/recent queries, fast-moving tech, company/product claims, quotes, sources that disagree, hurry, no web access) plus the full source-quality red-flag catalog. Read it when you hit one of those situations.
EXAMPLES.md — one full worked answer in the correct output format. Read it if you're unsure how the finished output should look.
README.md — why the skill exists, install notes, author. Not needed to run the skill.

The three jobs, always blended

Verify before claiming. Every factual statement is matched to a real source that was actually fetched and read — not a search snippet, not training memory.
Label uncertainty. Anything not fully verified gets an explicit confidence label with a reason. Silent uncertainty is a failure.
Self-audit before delivery. The answer is re-read for contradictions, unsourced numbers, vague dates, and banned phrases before it ships.

The point isn't pedantry. It's that anything the person repeats to a client, teammate, or audience survives scrutiny.

When to use this skill

Use it whenever the answer would contain factual content that could be repeated to a third party and being wrong would be embarrassing: research summaries, statistics, citations, vendor comparisons, "latest in X," "what does Y think about Z," market data, due diligence, evidence-backed recommendations.

Read the full file on GitHub · 195 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 · 195 lines · 171 tokens per session scan A 3d480e002b71

Subscribe to this mod's changes

no-bullshit-research is a skill published in the GitHub repository bpodhalicz/designer-claude-skills (8 stars, last pushed 4mo ago), licensed MIT. It adds 171 tokens to every session and 3,456 once invoked, about $0.0007 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 claude claude-skills design-tools ui-design ux-design

no-bullshit-research next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
no-bullshit-researchbpodhalicz/designer-claude-skills	Skill	8	4mo ago	MIT	A	171	Claude Code, Codex
ui-designerccwbb78/design-skills	Skill	12	4mo ago	none	A	58	Claude Code, Codex
refine-liveJakubantalik/transitions.dev	Skill	6.1k	8d ago	none	A	103	Claude Code, Codex
transitions-devJakubantalik/transitions.dev	Skill	6.1k	8d ago	none	A	410	Claude Code, Codex
transitions-ui-generationJakubantalik/transitions.dev	Skill	6.1k	8d ago	none	A	0	Claude Code, Codex
transitions-polishJakubantalik/transitions.dev	Skill	6.1k	8d ago	none	A	226	Claude Code, Codex
transitions-agentJakubantalik/transitions.dev	Skill	6.1k	8d ago	none	A	119	Claude Code, Codex