declarative-agent-sample-review

declarative-agent-sample-review is a skill for Claude Code, Codex from pnp/copilot-pro-dev-samples. It costs 69 tokens per session (716 once invoked), scanned A, original, MIT.

A review process for declarative agent samples, which are Microsoft 365 Copilot agent projects described by configuration files.

In plain words
What is it for?
It is for reviewing pull requests that add or change folders beginning with da- in the specified sample repository.
Why use it?
It provides checks for required folder names, manifest versions, project settings, and README structure before accepting a sample.

Skill for Claude CodeCodex

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/pnp/copilot-pro-dev-samples/declarative-agent-sample-review
Any agent
npx skills add pnp/copilot-pro-dev-samples --skill declarative-agent-sample-review
Clone the repo
git clone --depth 1 https://github.com/pnp/copilot-pro-dev-samples

Made for: Claude Code, Codex.

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 declarative-agent-sample-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pnp/copilot-pro-dev-samples/declarative-agent-sample-review.svg)](https://agentmods.dev/skills/pnp/copilot-pro-dev-samples/declarative-agent-sample-review)
Your own site
<a href="https://agentmods.dev/skills/pnp/copilot-pro-dev-samples/declarative-agent-sample-review"><img src="https://agentmods.dev/badge/skills/pnp/copilot-pro-dev-samples/declarative-agent-sample-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 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 $0.00069 $0.00716
Opus 5 $0.00034 $0.00358
Sonnet 5 $0.00014 $0.00143
Haiku 4.5 $0.00007 $0.00072

Measured 4d ago against content hash 3a93cccd28bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

declarative-agent-sample-review 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 4d 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.

.github/skills/declarative-agent-sample-review/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Declarative Agent Sample Review

Review declarative agent sample PRs (folders starting with da-) for compliance with repo guidelines.

Workflow

  1. Checkout PR: gh pr checkout <number>
  2. Verify sample folder starts with da-
  3. Run checks below, collecting comments (file, line, issue)
  4. Submit all comments in single API call (GitHub limitation)

Checks

1. Manifest Schema Versions

Fetch latest versions from Microsoft Learn docs (never use other samples as reference):

Manifest File Property Docs
App appPackage/manifest.json manifestVersion learn.microsoft.com/microsoft-365/extensibility/schema
Declarative Agent appPackage/*DeclarativeAgent.json version + $schema learn.microsoft.com/microsoft-365-copilot/extensibility/declarative-agent-manifest
API Plugin appPackage/ai-plugin.json schema_version learn.microsoft.com/microsoft-365-copilot/extensibility/api-plugin-manifest

2. m365agents.yml

  • No projectId - auto-generated on provision, must not be committed
  • Check both m365agents.yml and m365agents.local.yml

3. README.md

Compare against templates/da-declarative-agent/README.md:

  • Contributors section present with actual author names
  • Version history lists real author (not "Microsoft")
  • Tracking image uses markdown format at end of file:
    ![](https://m365-visitor-stats.azurewebsites.net/copilot-pro-dev-samples/<sample-folder>)
    
  • URLs consistent (avoid mixed en-us/ locales in same file)
  • No trailing --- at end

4. assets/sample.json

Compare against templates/sample-template.json:

  • name: pnp-copilot-pro-dev-<sample-folder>
  • url/downloadUrl: correct sample folder path
  • authors: matches actual contributors (verify against PR author)
  • URLs: consistent locale format

Submitting Reviews

GitHub API cannot add comments to pending reviews after creation. Collect all comments first.

Read the full file on GitHub · 89 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. 4d ago First seen · 89 lines · 69 tokens per session scan A 3a93cccd28bd

Subscribe to this mod's changes

declarative-agent-sample-review is a skill published in the GitHub repository pnp/copilot-pro-dev-samples (156 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 716 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.