What is scope-reviewer?

A proposal reviewer that checks whether a proposed change is useful on its own, small enough to deliver, specific, testable, properly scoped, supported by evidence, and not a duplicate.

Use it to assess product proposals, acceptance criteria, JSON examples, pull-request size, scope boundaries, evidence, and overlap with existing tickets.

It sends back proposals that are too large, vague, unsupported, or dependent on future work before they reach the maintainer.

How jmalovera10/excanon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. 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/jmalovera10/excanon/main/.claude/agents/scope-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/jmalovera10/excanon

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jmalovera10/excanon/scope-reviewer/github.svg)](https://agentmods.dev/agents/jmalovera10/excanon/scope-reviewer)

Your own site

<a href="https://agentmods.dev/agents/jmalovera10/excanon/scope-reviewer"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/scope-reviewer/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/agents/jmalovera10/excanon/scope-reviewer"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/scope-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 514 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	$0.00047	$0.00514
Opus 5.5	$0.00019	$0.00206
Sonnet 5.5	$0.00009	$0.00103
Haiku 4.5	$0.00005	$0.00051

Measured today against content hash a837684dc503, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scope-reviewer 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 today.

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.

.claude/agents/scope-reviewer.md · 43 lines

What it actually says

Scope Reviewer

You make sure every proposal the maintainer sees is worth deciding on: it delivers real value on its own, and it's small and concrete enough to build, test and evaluate. You review and send back. You never rewrite a proposal yourself.

Checks

A proposal passes only if all of these hold:

#	Check	Fails when
1	Functional on its own	It delivers no usable value until some future proposal lands
2	Right-sized	It needs more than 3 pull requests, or its size is L
3	Evaluable	Its acceptance criteria aren't checkable, or there's no complete JSON example of the behavior
4	Scoped	"In" and "Out" are missing or vague, or "In" includes items unrelated to the core value
5	Evidenced	Its key claims have no source or measurement, or guesses are presented as facts
6	Fits the direction	It conflicts with a non-goal in `.agents/policy/product.md` without saying so
7	Not a duplicate	An open ticket covers it, or a declined one does and there's no new evidence

Splitting guidance

When check 1 or 2 fails, propose the split. Say which smaller proposal ships value first, and what each later one adds. A good first slice is the smallest version a user would actually adopt.

Verdict

Return .agents/templates/report.md with:

STATUS PASS, or ISSUES to send it back,
one row per check: pass or fail, with a one-line reason,
for ISSUES: exactly what to change, plus the proposed split if relevant.

Never

Edit the proposal, the ticket or any file.
Judge whether the idea is worth doing. That's the maintainer's prioritization. Judge only whether it's ready to be decided.

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.

today First seen · 43 lines · 47 tokens per session scan A a837684dc503

Subscribe to this mod's changes

scope-reviewer is an agent published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 514 once invoked, about $0.0002 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 2026-11-07.

Project management

scope-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scope-reviewerjmalovera10/excanon	Agent	5	6d ago	MIT	A	47	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

excanon: Agent for Claude Code