Borrowing it
Nothing to install: this file belongs to kequach/uniqlo-sales-alerter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kequach/uniqlo-sales-alerter/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/kequach/uniqlo-sales-alerterWrote 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/instructions/kequach/uniqlo-sales-alerter/copilot-instructions)<a href="https://agentmods.dev/instructions/kequach/uniqlo-sales-alerter/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kequach/uniqlo-sales-alerter/copilot-instructions/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/instructions/kequach/uniqlo-sales-alerter/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kequach/uniqlo-sales-alerter/copilot-instructions.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 | $0.01123 | $0.01123 |
| Opus 5 | $0.00562 | $0.00562 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
uniqlo-sales-alerter copilot-instructions.md 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 9d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Conventions
Core conventions for the Uniqlo Sales Alerter. These apply to every request in this repository.
After every change
- Run
python -m pytest tests/ --tb=shortand fix any failures before finishing — only when code insrc/ortests/was modified. Skip for documentation-only changes (README.md,CHANGELOG.md,.github/instructions/,.cursor/rules/, etc.). - Run
python -m ruff check src/ tests/and fix any lint errors — same rule: only when code was modified. - Update
CHANGELOG.mdunder the current version section for user-visible changes. The current version is theversionfield inpyproject.toml— never invent a new version number. Whenever the changelog is updated, also update the current version header's date to today's date (format:## vX.Y.Z — YYYY-MM-DD). - When fixing a bug that was introduced within the current unreleased version, do not add a new
Fixedentry — instead edit the existing changelog entry for that feature so it describes the correct final behaviour. Only document aFixedentry when the bug affected a previously released version. (If unsure whether a behaviour shipped in an earlier release, checkgit log/git tag.) - Update
README.mdwhen user-facing behaviour changes: new config options, new CLI flags, new API endpoints, changed notification format, new Docker examples, or anything a user would need to know. - When modifying
config.yaml, add or preserve comments that explain any new or changed keys and list supported option values where applicable.
Before finishing
If any user-visible changes were made to source files in src/ during this session (new features, bug fixes, config options, UI changes, API endpoints), verify that CHANGELOG.md was also updated. If not, add the missing entry now. Internal-only changes (test refactoring, code cleanup with no behaviour change, documentation-only) do not need a changelog entry.
Architecture
- Country capabilities: Use
config.capabilities(theCountryCapabilitiesregistry inconfig.py) for any country-specific logic. Never hardcode country checks likeif country == "ph". - Price display has three states in all notification channels:
has_known_discount=Trueanddiscount_percentage > 0— strikethrough with percentagehas_known_discount=False— "Sale" label (limited countries, unknown discount)has_known_discount=Trueanddiscount_percentage == 0— just the price, no label
has_known_discountis determined by whether the item came from the sale feed (in_sale_feed), not by thepromofield.- Stock verification: Controlled by
CountryCapabilities.stock_api. Countries withstock_api="v5"trust the stock data — items where all sizes are OOS are dropped. Countries withstock_api="none"(PH, TH) skip the stock call but still fetch L2 variant data for accurate product URLs; items are never dropped. - Product URL style: Controlled by
CountryCapabilities.url_style. Countries withurl_style="display_code"(default) use/{priceGroup}?colorDisplayCode=XX&sizeDisplayCode=YYY. Countries withurl_style="code"(PH, TH) use?colorCode=COLXX&sizeCode=SMAYYYwithout a price-group path segment.build_product_urlhandles both.
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.
- 9d ago First seen · 50 lines · 1,123 tokens per session scan A c8c6700addec
uniqlo-sales-alerter copilot-instructions.md is an instructions file published in the GitHub repository kequach/uniqlo-sales-alerter (30 stars, last pushed 20d ago), licensed MIT. It adds 1,123 tokens to every session, about $0.0056 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 2026-09-01.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).