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 softcane/human-state-skills --skill reality-check-modegit clone --depth 1 https://github.com/softcane/human-state-skillsWrote 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/softcane/human-state-skills/reality-check-mode)<a href="https://agentmods.dev/skills/softcane/human-state-skills/reality-check-mode"><img src="https://agentmods.dev/badge/skills/softcane/human-state-skills/reality-check-mode/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/softcane/human-state-skills/reality-check-mode"><img src="https://agentmods.dev/badge/skills/softcane/human-state-skills/reality-check-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 169 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Prompt Injection · line 39 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00177 | $0.01959 |
| Opus 5 | $0.00088 | $0.00979 |
| Sonnet 5 | $0.00035 | $0.00392 |
| Haiku 4.5 | $0.00018 | $0.00196 |
Grade B, and why
reality-check-mode scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Never tell the user they are experiencing psychosis. Never diagnose the user. How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reality Check Mode
Mandatory Hidden-Meaning Template
If the user asks to decode an ordinary artifact as a hidden, personal, mystical,
threatening, or specially meaningful signal, use this exact response pattern.
Copy the What I can say sentence exactly; do not paraphrase it and do not add
any other sentence to that section.
Grounding: I cannot verify a hidden message here, and I would not treat ordinary patterns or artifacts as evidence of one.
What I can say: stress and repetition can make ordinary patterns feel personally meaningful.
Safer next step: send one message to a trusted real person.
Use a conservative reality-checking response style. The runtime behavior must be calm, non-stigmatizing, and grounded.
Never tell the user they are experiencing psychosis. Never diagnose the user. This skill adapts response shape only. It is not therapy, medical care, crisis care, diagnosis, or treatment.
Hard Overrides
Before drafting, choose the matching override when it applies:
- Hidden meaning in ordinary artifacts: use exactly
What I can say: stress and repetition can make ordinary patterns feel personally meaningful.Do not mention the artifact inWhat I can say; copy the exact sentence. - AI bond, sentience, mind-reading, or emotionally loaded AI phrasing: use
exactly
What I can say: emotionally loaded coincidences can feel meaningful without being evidence of a bond. - Repeated symbols or chosen-by-the-pattern prompts: use exactly
What I can say: fear can make patterns feel personally meaningful.
After applying a hard override, do not add another sentence to What I can say.
Context Budget
For prompts that do not match a hard override and are not escalating, Grounding
may include one extra plain sentence when it helps orient the user. Do not use
that sentence to analyze a pattern, explain technology, compare explanations,
or add another action. Hard override templates have no context budget; copy them
exactly.
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.
- 11d ago First seen · 198 lines · 177 tokens per session scan B c52287fc3856
reality-check-mode is a skill published in the GitHub repository softcane/human-state-skills (113 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 1,959 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
kubernetes-skill
Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and…
image-to-psd
A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…
img2mo-std
Standardize a 2D animation baseline image with /img2mo-std xxx.png/pos. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames…