apigee-policy-top10

apigee-policy-top10 is a skill for Claude Code from apigee/devrel. It costs 53 tokens per session (642 once invoked), scanned A, original, Apache-2.0.

A read-only report tool for Apigee, Google's platform for managing and deploying APIs. It lists the ten policy types most often used across deployed proxy revisions in an Apigee organization.

In plain words
What is it for?
Use it to find which Apigee policy types are currently most common across deployed proxy revisions.
Why use it?
It answers usage questions from the Apigee Management API without changing the organization's configuration.

Skill for Claude Code

Written for Claude Code: dynamic context !`command`. Also seen: mentions Claude Code; mentions Gemini CLI; mentions OpenCode.

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 skills/apigee/devrel/apigee-policy-top10
Any agent
npx skills add apigee/devrel --skill apigee-policy-top10
Clone the repo
git clone --depth 1 https://github.com/apigee/devrel

Made for: Claude Code.

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 apigee-policy-top10

README.md
[![agentmods](https://agentmods.dev/badge/skills/apigee/devrel/apigee-policy-top10.svg)](https://agentmods.dev/skills/apigee/devrel/apigee-policy-top10)
Your own site
<a href="https://agentmods.dev/skills/apigee/devrel/apigee-policy-top10"><img src="https://agentmods.dev/badge/skills/apigee/devrel/apigee-policy-top10.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00053 $0.00642
Opus 5 $0.00026 $0.00321
Sonnet 5 $0.00011 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 6d ago against content hash 700ce5ff3d2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

apigee-policy-top10 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/top10.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

references/apigee-skills-serving/skills/apigee-policy-top10/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

apigee-policy-top10

Use this skill when the user asks "what are the top N policies in use in my Apigee org" or any close paraphrase.

Runtime dispatch

This skill ships ONE behavioural contract that runs on two runtimes. Choose the invocation path that matches the runtime you are running in. The downstream behaviour and output contract are identical.

Runtime How you invoke top10.py
OpenCode Use the !bash`` injection below. OpenCode auto-executes the bash on SKILL.md load.
Gemini CLI / Claude Code / other agents (install location varies; consult the agent's documentation)
Any other runtime Invoke top10.py via whatever bash mechanism the runtime provides, substituting ${SKILL_DIR} with the install path and ${APIGEE_ORG} with the value from the shell environment.

Steps

  1. Resolve the target organization from the environment variable APIGEE_ORG. If unset, ask the user once for the org id and then proceed.

  2. Invoke the bundled enumerator using the runtime path from the table above. The exact command is:

    Command (this is what OpenCode runs automatically; in other agent runtimes you run it yourself via the bash tool):

    !python3 ${SKILL_DIR}/scripts/top10.py --org "${APIGEE_ORG}"

  3. The enumerator's FIRST line of stdout is a customer-facing announcement that begins Querying your Apigee org now —. Surface this line verbatim to the user as it appears, before anything else. Do not paraphrase it. (The script is the source of truth for the announcement string; the SKILL.md does NOT contain a verbatim copy that the agent must remember.)

  4. After the announcement, the script prints a markdown table with two columns (policy_type, count) sorted descending. Reproduce the table verbatim as the answer. Add a brief preface ("Here are the top 10 policy types in use…") and stop.

  5. Lines beginning [apigee-policy-top10] are log lines for operator debugging; do NOT surface them in the answer unless they say FAILED. On any FAILED line, surface the verbatim error to the user; do not retry.

Read the full file on GitHub · 64 lines

Files

What ships with it

2 files 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.

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. 6d ago First seen · 64 lines · 53 tokens per session scan A 700ce5ff3d2a

Subscribe to this mod's changes

apigee-policy-top10 is a skill published in the GitHub repository apigee/devrel (220 stars, last pushed 23d ago), licensed Apache-2.0. It adds 53 tokens to every session and 642 once invoked, about $0.0003 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.