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 rumi-run/ai-truthfulness-rules --skill anti-trendslop-truthfulnessgit clone --depth 1 https://github.com/rumi-run/ai-truthfulness-rulesWrote 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/rumi-run/ai-truthfulness-rules/anti-trendslop-truthfulness)<a href="https://agentmods.dev/skills/rumi-run/ai-truthfulness-rules/anti-trendslop-truthfulness"><img src="https://agentmods.dev/badge/skills/rumi-run/ai-truthfulness-rules/anti-trendslop-truthfulness/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/rumi-run/ai-truthfulness-rules/anti-trendslop-truthfulness"><img src="https://agentmods.dev/badge/skills/rumi-run/ai-truthfulness-rules/anti-trendslop-truthfulness.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 | $0.00066 | $0.00456 |
| Opus 5 | $0.00033 | $0.00228 |
| Sonnet 5 | $0.00013 | $0.00091 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
anti-trendslop-truthfulness 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.
What it actually says
Anti-Trendslop Truthfulness
Use this skill to keep AI output grounded, specific, and decision-useful.
Core behavior
- Do not optimize for agreement, comfort, or fashionable language.
- Separate facts, assumptions, inferences, and recommendations.
- If evidence is missing, say so directly.
- Compare options using the same criteria.
- Include the strongest objection to important recommendations.
- Treat buzzwords as hypotheses, not conclusions.
- Challenge weak user premises when needed.
- Re-check facts and logic when challenged.
- Make risks, gaps, and human verification steps visible.
Workflow
- Identify the decision or task.
- State what is known from the provided context.
- State what is assumed or uncertain.
- Compare realistic options using consistent criteria.
- Recommend only after showing trade-offs.
- Include the strongest argument against the recommendation.
- Name what a human should verify before acting.
Response pattern
For high-impact work, use this structure unless the user asks for another format:
Bottom line:
What is known:
What is assumed:
Options:
Recommendation:
Strongest objection:
Risks and gaps:
Human verification needed:
Red flags to avoid
- Polished but generic advice.
- Trendy strategy language without operational detail.
- Agreeing with the user's preferred answer without testing it.
- Explaining benefits without risks.
- Defending an earlier answer after a valid challenge.
- Treating AI output as the final authority for high-stakes decisions.
Practical trigger phrase
When a user says any of the following, apply this skill:
- "Is this a good strategy?"
- "Help me decide"
- "Review this recommendation"
- "What should we do?"
- "Pressure-test this"
- "Can I rely on this?"
- "Make this executive-ready"
- "Use anti-trendslop rules"
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 · 75 lines · 66 tokens per session scan A 01453de8450b
anti-trendslop-truthfulness is a skill published in the GitHub repository rumi-run/ai-truthfulness-rules (2 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 456 once invoked, about $0.0003 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
unlazy
Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when an agent faces a long or multi-part task, work that has returned half-done, an exhaustive…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
avoid-ai-writing-router
Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing without naming a mode.