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-03-constraint-pingit 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-03-constraint-pin)<a href="https://agentmods.dev/skills/arunveersingh/ai/day-03-constraint-pin"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-03-constraint-pin/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-03-constraint-pin"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-03-constraint-pin.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 | $0.00065 | $0.00549 |
| Opus 5.5 | $0.00026 | $0.00220 |
| Sonnet 5.5 | $0.00013 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
constraint-pin 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.
What it actually says
Constraint pin
Context window amnesia is when a rule from early in a thread stops shaping answers later, with no warning. Fix it in two moves: ask with the rules re-sent next to the risky request, then verify the output against each rule, and move the most important one into a check outside the chat.
Paste Part A with the risky ask (not only at the start). Do Part B yourself. Swap brackets. Tighten or drop rules if you need to.
Part A — Ask (paste / adapt)
CONSTRAINTS (apply to every answer in this session):
1. [HARD RULE]
2. [HARD RULE]
3. [HARD RULE]
Task: [YOUR REQUEST]
Rules:
1. Before answering, list each CONSTRAINTS item that applies to this task and how your answer meets it.
2. If the task conflicts with any CONSTRAINTS item, stop and name the conflict. Do not resolve it silently.
3. If you are not sure whether a constraint applies, say UNKNOWN and ask. Do not guess.
Long thread? Ask for a handoff note that copies CONSTRAINTS word for word plus decisions so far. Check the copy against your original, then start a new chat with it.
Part B — Verify (you do this)
- Score the output, not the claim. Pass or fail each CONSTRAINTS item against the actual code or text, not against the model's "how I met it" list.
- Move the top rule out of the chat. Turn it into a test, lint rule, or CI step that fails when the rule is broken.
- Probe before critical asks. Without re-sending, ask it to quote CONSTRAINTS exactly. Wrong or missing → start fresh with a handoff note.
- Silent break = failed draft. If a rule was broken and the conflict was never named, re-run with Part A even if you can patch the line yourself.
Done when: every CONSTRAINTS item has a pass/fail against the output, and your most important rule has a check that runs outside the chat (or a written plan for one).
Lesson: Day 3 — Context Window Amnesia
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 · 40 lines · 65 tokens per session scan A 52be4845fea9
constraint-pin is a skill published in the GitHub repository arunveersingh/ai (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 549 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…