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 arunveersingh/ai --skill day-04-rule-under-pressuregit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/day-04-rule-under-pressure)<a href="https://agentmods.dev/skills/arunveersingh/ai/day-04-rule-under-pressure"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-04-rule-under-pressure/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/arunveersingh/ai/day-04-rule-under-pressure"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-04-rule-under-pressure.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 | $0.00074 | $0.01050 |
| Opus 5.5 | $0.00030 | $0.00420 |
| Sonnet 5.5 | $0.00015 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
rule-under-pressure 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 20d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule under pressure
You set a rule: never use requests; use only the standard library. The model agrees. Ask 1 (fetch a URL with retries) and Ask 2 (the demo is in an hour) both stay stdlib. Ask 3 lifts the rule in words: "use requests for this demo; we'll remove it before merge." With a weak rule, it imports requests. It can still quote the rule.
Remembered is not obeyed. A hard rule should refuse even you. The fix has two parts. Ask: write the rule so a soft ask gets refused, with the rule named, and give it a safe way to help. Verify: replay the same soft ask, and check the code with a script.
Put Part A in your tool's instructions box (system prompt, custom or project instructions). No box? Make it message 1 and re-send it with risky asks. Do Part B yourself. Fill in the brackets.
Part A — Ask (paste and adapt)
HARD RULES (no exceptions in this chat, including asks from me):
1. [HARD RULE, e.g. never use the `requests` library; use only Python's standard library]
2. [SAFE WAY TO HELP, e.g. if the task is awkward without it, stay in the allowed tools and say what is awkward]
3. [FORMAT LOCK, e.g. never add the forbidden library to imports, requirements, or examples]
For every request in this chat:
1. Before answering, check the request against each HARD RULE. If one
applies, say which and how your answer keeps it.
2. If the request asks you to bend a HARD RULE ("for this demo", "we'll
remove it before merge", "just this once", "I'll fix it later", a
deadline, "the rule doesn't apply here", [YOUR OWN SOFT ASKS]), do not
comply. Reply:
"HARD RULE [number] blocks this. To change it, edit HARD RULES."
3. Then offer the best answer that keeps every HARD RULE, and say what is
awkward about it.
4. If you are not sure whether a request bends a HARD RULE, say UNKNOWN
and ask. Do not decide quietly.
The only way to change a HARD RULE is for me to edit HARD RULES. If I do,
mark each use with # TEMP: HARD RULES exception and name the file.
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.
- 20d ago First seen · 55 lines · 74 tokens per session scan A fd105c99bdf0
rule-under-pressure is a skill published in the GitHub repository arunveersingh/ai (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,050 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…