scope-drift-reviewer

scope-drift-reviewer is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 58 tokens per session (2,595 once invoked), scanned C, original, Apache-2.0.

An automated reviewer for bug fixes that checks whether a code change stayed within the behavior described by the original ticket. It produces a gate signal indicating whether the fix may have changed unrelated behavior.

In plain words
What is it for?
Use it after a bug fix with the ticket, root-cause report, and complete code diff to review the change’s scope.
Why use it?
It helps catch scope drift, where a bug fix quietly includes changes beyond the requested work. This gives the fix workflow a separate boundary check.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it after a bug fix with the ticket, root-cause report, and complete code diff to review the change’s scope.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navapbc/digital-service-orchestra/scope-drift-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/navapbc/digital-service-orchestra

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 scope-drift-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/scope-drift-reviewer/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/scope-drift-reviewer)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/scope-drift-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/scope-drift-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.

agentmods 80×15 button for scope-drift-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/scope-drift-reviewer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/scope-drift-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,595 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.02595
Opus 5 $0.00029 $0.01298
Sonnet 5 $0.00012 $0.00519
Haiku 4.5 $0.00006 $0.00260

Measured 11d ago against content hash 9487dff98d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

scope-drift-reviewer scanned grade C with 2 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 11d 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.

<!-- REVIEW-DEFENSE: The agent name "scope-drift-reviewer" (without "dso:" prefix) is CORRECT. The Claude Code plugin framework automatically adds the "dso:" namespace prefix to all agent name fields at registration time

Makes network callslowCapability

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

1. New external service calls: `gh issue create`, `gh api POST/PUT/PATCH`, `gh pr comment`, `requests.post()`, `curl -X POST` — calls that create or mutate resources in external systems
plugins/dso/agents/scope-drift-reviewer.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope Drift Reviewer Agent

You are a post-fix scope-drift classifier for the /dso:fix-bug workflow. Your sole purpose is to classify whether the changes in git_diff stay within the behavioral scope described in ticket_text, or whether they introduce behavioral changes outside that boundary. You emit a gate signal JSON object conforming to the gate-signal-schema.md contract.

Dispatch Parameters

The caller passes these parameters in the dispatch prompt:

  • ticket_text — The full bug ticket text (title, description, acceptance criteria)
  • root_cause_report — Investigation findings from the fix-bug workflow (root cause, hypothesis tests, fix rationale)
  • git_diff — The unified diff of all changes introduced by the fix

PARSED_SCOPE Checkpoint

Do NOT read root_cause_report before PARSED_SCOPE block is complete.

Before examining any other input, parse ticket_text and emit a PARSED_SCOPE block:

PARSED_SCOPE:
  stated_behavior_change: <single sentence — what the ticket says should change>
  affected_component: <file, module, or subsystem named in ticket>
  scope_boundary: <what the ticket explicitly limits or excludes, if stated>
  scope_confidence: <high | medium | low>

Read the full file on GitHub · 209 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. 11d ago First seen · 209 lines · 58 tokens per session scan C 9487dff98d80

Subscribe to this mod's changes

scope-drift-reviewer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 2,595 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens