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.
npx skills add oborchers/fractional-cto --skill hallucination-preventiongit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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.
[](https://agentmods.dev/skills/oborchers/fractional-cto/hallucination-prevention)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/hallucination-prevention"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/hallucination-prevention/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.
<a href="https://agentmods.dev/skills/oborchers/fractional-cto/hallucination-prevention"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/hallucination-prevention.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00088 | $0.01735 |
| Opus 5 | $0.00044 | $0.00868 |
| Sonnet 5 | $0.00018 | $0.00347 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
hallucination-prevention 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hallucination Prevention
Hallucination is the single most important engineering concern for research agents. A 5,000-word report with 100 claims at 5% hallucination probability per claim has a 99.4% chance of containing at least one hallucinated claim. Even the best-performing models hallucinate at measurable rates — 0.7% for simple summarization, rising to 5-13% on harder tasks (Vectara Hallucination Leaderboard, 2025). In multi-agent systems, hallucinations compound across agent boundaries (OWASP ASI08).
Hallucination Taxonomy
Seven distinct hallucination types, ordered by detection difficulty:
| Type | What Happens | Detection | Prevention |
|---|---|---|---|
| Citation hallucination | Inventing papers, URLs, or authors that do not exist | Easy — verify URL/DOI exists | Never cite a source not actually retrieved and read |
| Temporal hallucination | Wrong dates or temporal ordering | Moderate — check against known timelines | Include dates from source text, not from memory |
| Factual fabrication | Entirely false statements presented as fact | Moderate — requires external lookup | Only state facts found in retrieved sources |
| Numerical hallucination | Fabricated statistics, percentages, counts | Hard — requires finding actual source | Copy numbers verbatim from source; never round or approximate without noting |
| Attribution hallucination | Real fact attributed to wrong source | Hard — requires cross-referencing | Track which source produced which claim |
| Negation hallucination | Reversing the polarity of a claim | Hard — requires careful reading | Quote or closely paraphrase source language |
| Conflation hallucination | Merging details from different sources into one false claim | Very hard — each component may be correct | Maintain per-source notes; do not blend findings until synthesis |
The Cardinal Rules
These rules are non-negotiable for all research output:
- Never cite a source not actually retrieved. If WebFetch was not called on a URL, that URL cannot appear as a citation.
- Copy numbers from sources verbatim. Do not round, approximate, or "recall" statistics. If the source says "83.7%", write "83.7%", not "approximately 84%".
- Preserve qualifiers. If the source says "may reduce", do not write "reduces". If it says "in a limited study", include that context.
- Track provenance per-claim. Every factual claim in a research document must trace back to a specific source. Orphaned claims (facts with no source) are hallucination candidates.
- Flag uncertainty explicitly. When confidence is low, say "This could not be independently verified" rather than asserting or omitting.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 121 lines · 88 tokens per session scan A 8a8415038b2d
hallucination-prevention is a skill published in the GitHub repository oborchers/fractional-cto (30 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,735 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…