Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sillyDaibo/reasflow-devnpx agentmods add skills/sillydaibo/reasflow-dev/anti-hallucination-markersWrote 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/sillydaibo/reasflow-dev/anti-hallucination-markers)<a href="https://agentmods.dev/skills/sillydaibo/reasflow-dev/anti-hallucination-markers"><img src="https://agentmods.dev/badge/skills/sillydaibo/reasflow-dev/anti-hallucination-markers/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/sillydaibo/reasflow-dev/anti-hallucination-markers"><img src="https://agentmods.dev/badge/skills/sillydaibo/reasflow-dev/anti-hallucination-markers.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 | $0.00028 | $0.00445 |
| Opus 5 | $0.00014 | $0.00222 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
anti-hallucination-markers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Installed Root
Resolve the installed reasflow-dev private skills root before running packaged scripts:
REASFLOW_PRIVATE_SKILLS_ROOT="${REASFLOW_PRIVATE_SKILLS_ROOT:-}"
if [ -z "$REASFLOW_PRIVATE_SKILLS_ROOT" ]; then
if [ -d ./.codex/reasflow-skills ]; then
REASFLOW_PRIVATE_SKILLS_ROOT="$(pwd)/.codex/reasflow-skills"
elif [ -d "$HOME/.codex/reasflow-skills" ]; then
REASFLOW_PRIVATE_SKILLS_ROOT="$HOME/.codex/reasflow-skills"
else
echo "reasflow private skills not found in ./.codex/reasflow-skills or $HOME/.codex/reasflow-skills" >&2
exit 1
fi
fi
Anti-Hallucination Markers
Overview
Mark weak spots while drafting instead of letting them ship as confident prose. Unsupported novelty, performance, or scope claims should stay visibly flagged until evidence lands.
Marker Set
[needs-citation]for factual claims without a source[needs-result]for performance or ablation claims without experiment evidence[scope-check]for claims that overreach the actual setting[terminology-check]for wording that does not match the paper body[remove-if-unproven]for claims that may need deletion instead of repair
Workflow
- Draft the paragraph normally.
- Tag every sentence that depends on evidence outside the current draft.
- Resolve or delete marked claims before final polishing.
- Remove markers only after the supporting section, figure, table, or citation is real.
- Treat any remaining marker as a failed deliverable; markers are drafting aids, not acceptable final output.
Deliverables
- marked-up intro or abstract draft
- evidence ledger for every flagged sentence
- deletion list for claims that stayed unsupported
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.
- 11d ago First seen · 47 lines · 28 tokens per session scan A b4868320ad37
anti-hallucination-markers is a skill published in the GitHub repository sillyDaibo/reasflow-dev (2 stars, last pushed 15d ago), licensed MIT. It adds 28 tokens to every session and 445 once invoked, about $0.0001 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.
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…