What is scope-contract?

A scope manifest workflow that records what a newsletter run is expected to cover, including versions, sources, dates, and categories. A manifest is a machine-readable checklist used for later validation.

Use it at the start and end of a newsletter run to create the expected-scope JSON file and produce validation results after the newsletter is assembled.

It makes the pipeline's intended boundaries explicit before work begins. After assembly, it checks whether the finished newsletter matches those expectations.

How briancl2/CustomerNewsletter configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to briancl2/CustomerNewsletter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/briancl2/CustomerNewsletter/main/.github/skills/scope-contract/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/briancl2/CustomerNewsletter

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/briancl2/customernewsletter/scope-contract/github.svg)](https://agentmods.dev/skills/briancl2/customernewsletter/scope-contract)

Your own site

<a href="https://agentmods.dev/skills/briancl2/customernewsletter/scope-contract"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/scope-contract/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/briancl2/customernewsletter/scope-contract"><img src="https://agentmods.dev/badge/skills/briancl2/customernewsletter/scope-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,635 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.01635
Opus 5.5	$0.00031	$0.00654
Sonnet 5.5	$0.00015	$0.00327
Haiku 4.5	$0.00008	$0.00163

Measured 2mo ago against content hash dd3e0d6d4134, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scope-contract 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 2mo 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/scope-contract/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Contract

Generate a testable scope manifest before the pipeline runs, then validate the newsletter output against it after assembly.

Quick Start

Pre-Pipeline (Phase 0)

Run python3 tools/generate_scope_contract.py <START_DATE> <END_DATE> (the helper reads the date range from these arguments)
If it succeeds, use the generated manifest as the Phase 0 artifact
Only fall back to manual source inspection if the helper cannot resolve the range
Verify the output at workspace/newsletter_scope_contract_YYYY-MM-DD.json

Post-Pipeline (after Phase 4.5)

Read scope manifest
Read final newsletter
Run validation checks
Write test results to workspace/newsletter_scope_results_YYYY-MM-DD.md

Scope Manifest Format

{
  "date_range": {
    "start": "YYYY-MM-DD",
    "end": "YYYY-MM-DD",
    "previous_newsletter_end": "YYYY-MM-DD",
    "gap_days": 0
  },
  "expected_versions": {
    "vscode": ["v1.108", "v1.109"],
    "visual_studio": ["18.2.x"],
    "jetbrains": ["1.5.60", "1.5.61", "1.5.62", "1.5.63", "1.5.64"],
    "xcode": ["0.46.0", "0.47.0"],
    "copilot_cli": ["v0.0.400+"]
  },
  "expected_sources": [
    "github.blog/changelog/YYYY/MM/",
    "github.blog/news-insights/company-news/",
    "code.visualstudio.com/updates/v1_NNN",
    "plugins.jetbrains.com/api/plugins/17718/updates",
    "github.com/github/CopilotForXcode/releases",
    "devblogs.microsoft.com/visualstudio/",
    "resources.github.com/events/"
  ],
  "expected_categories": [
    "Security & Compliance",
    "AI & Automation",
    "Platform & DevEx",
    "Enterprise Administration",
    "Code Quality",
    "IDE Updates"
  ],
  "expected_event_date_range": {
    "earliest": "YYYY-MM-DD",
    "latest": "YYYY-MM-DD"
  }
}

Pre-Pipeline Workflow

Step 1: Determine Date Range Boundaries

Read the requested DATE_RANGE (start, end)
First try python3 tools/generate_scope_contract.py <START_DATE> <END_DATE>
If the helper reuses an exact archived contract, keep that historical boundary metadata
If the helper cannot resolve the range, inspect archive/ manually for the previous newsletter end date and any gap
Record in manifest

Read the full file on GitHub · 175 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.

2mo ago First seen · 175 lines · 77 tokens per session scan A dd3e0d6d4134

Subscribe to this mod's changes

scope-contract is a skill published in the GitHub repository briancl2/CustomerNewsletter (11 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,635 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 2026-08-30.

Planning Research agentic-workflows agents copilot llmops mkdocs newsletter

scope-contract next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scope-contractbriancl2/CustomerNewsletter	Skill	11	5mo ago	MIT	A	77	Claude Code, Codex
trulens-diagnosistruera/trulens	Skill	3.6k	yesterday	MIT	A	17	Claude Code, Codex
agents-sdk-dotnet-activityhandler-migrationmicrosoft/Agents	Skill	1.1k	yesterday	MIT	A	76	Claude Code
agents-sdk-dotnetmicrosoft/Agents	Skill	1.1k	yesterday	MIT	A	112	Claude Code
agents-sdk-typescript-otelmicrosoft/Agents	Skill	1.1k	yesterday	MIT	A	88	Claude Code
bf-to-agents-sdk-dotnet-migrationmicrosoft/Agents	Skill	1.1k	yesterday	MIT	A	56	Claude Code
github-review-prfeiskyer/claude-code-settings	Skill	1.7k	yesterday	MIT	A	90	Claude Code

CustomerNewsletter: Skill for Claude Code