agentmods.dev

Purchasely-AI-Plugin CLAUDE.md

Purchasely-AI-Plugin CLAUDE.md is an instructions file for coding agents from Purchasely/Purchasely-AI-Plugin. It costs 4,273 tokens per session, scanned D, original, MIT.

Repository instructions for Purchasely-AI-Plugin. They define how to maintain the changelog, prepare releases, and keep the plugin's references and publishing metadata consistent.

In plain words
What is it for?
Use them when changing the plugin, updating CHANGELOG.md, cutting a release, or refreshing its listing on agentskill.sh.
Why use it?
They prevent user-visible changes and releases from being documented or published inconsistently.

Instructions file

not rated 2 3d ago D scan 4,273 tokens original MIT
View the source file Purchasely/Purchasely-AI-Plugin
Install

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.

agentmods
npx agentmods add instructions/purchasely/purchasely-ai-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/Purchasely/Purchasely-AI-Plugin

Wrote 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.

agentmods badge for Purchasely-AI-Plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/purchasely/purchasely-ai-plugin/claude-md.svg)](https://agentmods.dev/instructions/purchasely/purchasely-ai-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/purchasely/purchasely-ai-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/purchasely/purchasely-ai-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,273 This file is loaded in full into every session.
When invoked 4,273 The same file — it is already loaded in full.
Security scan D 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.04273 $0.04273
Opus 5 $0.02136 $0.02136
Sonnet 5 $0.00855 $0.00855
Haiku 4.5 $0.00427 $0.00427

Measured 5d ago against content hash e65446580f7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

Purchasely-AI-Plugin CLAUDE.md scanned grade D with 3 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 5d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- rtk-instructions v2 -->

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const r = await fetch("https://agentskill.sh/api/skills/submit", { method: "POST",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

### curl / wget — BLOCKED
CLAUDE.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Purchasely-AI-Plugin

Repository conventions for anyone (human or LLM) editing this plugin.

CHANGELOG must be kept up to date

Every PR that adds, changes, removes, or deprecates anything user-visible must update CHANGELOG.md:

  1. Add the entry under the top-level ## [Unreleased] section, in the appropriate sub-section: Added, Changed, Removed, Deprecated, Fixed, Security.
  2. Keep entries short, factual, and user-facing. Example: Added references/concepts/promotional-offers.md — covers Apple promo offers, Google developer-determined offers, offer codes — not Reworked the references directory.
  3. When cutting a release, rename [Unreleased] to [X.Y.Z] — YYYY-MM-DD and add a fresh empty [Unreleased] section at the top — see Release process below for the full, authoritative list of manifests to bump.
  4. Format follows Keep a Changelog. Versioning follows SemVer.

Rule of thumb: if you wouldn't write the change in the release notes a client reads, you probably don't need a CHANGELOG entry. Otherwise, write one.

Release process

Releases are cut directly on main — there is no release PR.

  1. In CHANGELOG.md, rename [Unreleased] to [X.Y.Z] — YYYY-MM-DD and add a fresh empty [Unreleased] section above it.
  2. Bump version in every manifest — this list is exhaustive; gemini-extension.json was missed in earlier releases and stayed at 1.1.0 until this PR caught it up:
    • .claude-plugin/plugin.json
    • .claude-plugin/marketplace.json
    • .cursor-plugin/plugin.json
    • .cursor-plugin/marketplace.json
    • purchasely/.claude-plugin/plugin.json
    • purchasely/.cursor-plugin/plugin.json
    • purchasely/.codex-plugin/plugin.json
    • package.json
    • gemini-extension.json
  3. Commit directly on main: chore(release): X.Y.Z.
  4. Tag and release: git tag X.Y.Z && gh release create X.Y.Z. Tags are bare SemVer, no v prefix (confirmed via git tag --sort=-creatordate, e.g. 2.0.0-rc.6, 2.0.0-rc.5, …) — keep using that format.
  5. Versioning: never bump a major version without explicit sign-off from the user; default to a minor (or patch) bump.
  6. If the release changed a name: or description: field in any SKILL.md frontmatter, trigger the agentskill.sh re-scan described below.

Read the full file on GitHub · 322 lines

Changes

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.

  1. 5d ago First seen · 322 lines · 4,273 tokens per session scan D e65446580f7d

Subscribe to this mod's changes

Purchasely-AI-Plugin CLAUDE.md is an instructions file published in the GitHub repository Purchasely/Purchasely-AI-Plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 4,273 tokens to every session, about $0.0214 per session on Opus 5. A static security scan graded it D with 3 findings (hidden instructions, sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflowReleases
Related

Other instructions, from other repositories

planning-with-files AGENTS.md

AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.

OthmanAdi/planning-with-files · 2,236 tokens

openrouter-mcp-multimodal AGENTS.md

AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 793 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

ai-usagebar CLAUDE.md

Claude Code instructions for akitaonrails/ai-usagebar, covering claude.md, release checklist — must do all of these, hard invariants — never break these, secret-discipline rules (learned the hard way) and live api smoke discipline.

akitaonrails/ai-usagebar · 4,263 tokens

living-manual CLAUDE.md

Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.

dougstanford/living-manual · 1,108 tokens

yandex360-mcp CLAUDE.md

Claude Code instructions for pa1ch/yandex360-mcp, covering claude.md — гайд для ассистента, как устроен релиз (всё автоматически по тегу), процедура релиза (шаги ассистента), гарды and архитектура (кратко).

pa1ch/yandex360-mcp · 1,005 tokens