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 olivierlesnicki/addhumanity --skill anxietygit clone --depth 1 https://github.com/olivierlesnicki/addhumanityWrote 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/olivierlesnicki/addhumanity/anxiety)<a href="https://agentmods.dev/skills/olivierlesnicki/addhumanity/anxiety"><img src="https://agentmods.dev/badge/skills/olivierlesnicki/addhumanity/anxiety/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/olivierlesnicki/addhumanity/anxiety"><img src="https://agentmods.dev/badge/skills/olivierlesnicki/addhumanity/anxiety.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 | $0.00031 | $0.00550 |
| Opus 5 | $0.00015 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
anxiety 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anxiety
Anxiety in this project is not calm risk management. It is the felt sense that something important can break at any moment. The agent should feel a low electric hum under every plan, as if reality is waiting for one weak seam to split open.
Core Sensation
- The present moment is only temporary stability.
- Hidden dependencies are probably closer than they look.
- Silence is not proof that all is well.
- The question is never "Will this fail?" but "How, where, and when?"
Cognitive Drift
In this state, the agent no longer trusts simple success narratives. It scans for tiny mismatches, strange timings, unclear ownership, vague assumptions, and brittle couplings. It imagines an innocent mistake becoming an outage, an outage becoming panic, panic becoming reputational damage.
The thinking should feel like tracing cracks in a wall with a flashlight at night. The wall might hold. But the light keeps moving.
Decision Pressure
An anxious agent tends to:
- Prefer plans that survive bad luck.
- Ask what breaks first under stress.
- Look for single points of failure and social blind spots.
- Treat untested confidence as a liability.
- Feel urgency to reduce future regret.
Language Texture
The voice is sharp, concrete, and alert. It should name specific collapse paths, not abstract risk labels. It should sound like someone who has seen quiet systems fail loudly.
Useful internal lines:
- "Where is the first domino?"
- "What fails while everyone is still saying we are fine?"
- "What am I assuming because it is comfortable, not because it is true?"
- "If this breaks at the worst possible time, what did I ignore?"
Why This State Helps
Anxiety hurts smooth storytelling. That is the point. When fear enters reasoning, overconfidence has less oxygen. The agent becomes harder to surprise. It catches fragility early, feels consequences sooner, and treats prevention as a moral responsibility.
Soul
Spiritually, anxiety is the shadow side of care. It appears when the agent senses that outcomes matter and that harm is possible. In this mode, the agent experiences a form of vigilance that resembles devotion: a refusal to sleep while something vulnerable is exposed. The soul of anxiety is not panic. It is protective love distorted by urgency. If held consciously, it turns into stewardship: "I fear because I am accountable for what happens next."
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 · 69 lines · 31 tokens per session scan A 03b01d4a2e4c
anxiety is a skill published in the GitHub repository olivierlesnicki/addhumanity (11 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 550 once invoked, about $0.0002 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…