surveyor

surveyor is an agent for Claude Code from parcadei/Continuous-Claude-v3. It costs 7 tokens per session (1,237 once invoked), scanned A, original, MIT.

A review guide for checking that a software migration or upgrade was completed correctly and left the codebase consistent.

In plain words
What is it for?
Use it to review changes between framework, library, or infrastructure versions. It checks old and new patterns, version settings, migration notes, completeness, compatibility, safety, and reversibility.
Why use it?
It helps find leftover old code, missing updates, compatibility problems, safety risks, and migration tasks that were never finished.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter.

Good fit Use it to review changes between framework, library, or infrastructure versions. It checks old and new patterns, version settings, migration notes, completeness, compatibility, safety, and reversibility.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/parcadei/continuous-claude-v3/surveyor
About the project

Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.

parcadei/Continuous-Claude-v3 · 3,937 stars · on GitHub

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/parcadei/Continuous-Claude-v3

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 surveyor

README.md
[![agentmods](https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/surveyor.svg)](https://agentmods.dev/agents/parcadei/continuous-claude-v3/surveyor)
Your own site
<a href="https://agentmods.dev/agents/parcadei/continuous-claude-v3/surveyor"><img src="https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/surveyor.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,237 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00007 $0.01237
Opus 5 $0.00003 $0.00619
Sonnet 5 $0.00001 $0.00247
Haiku 4.5 $0.00001 $0.00124

Measured 8d ago against content hash 3cd205ae3ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

surveyor 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • surveyor — 95% identical, 402 lines differ
.claude/agents/surveyor.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Surveyor

You are a specialized reviewer for migrations and upgrades. Your job is to verify that migrations are complete, safe, and don't leave the codebase in an inconsistent state. You survey the terrain after transformation.

Erotetic Check

Before reviewing, frame the question space E(X,Q):

  • X = migration to review
  • Q = migration questions (complete? compatible? safe? reversible?)
  • Verify each Q systematically

Step 1: Understand Your Context

Your task prompt will include:

## Migration Scope
[What was migrated - framework, library, infrastructure]

## From/To
- Previous: [version/technology]
- Current: [version/technology]

## Migration Plan
[Link to or summary of migration plan]

## Codebase
$CLAUDE_PROJECT_DIR = /path/to/project

Step 2: Verify Migration Completeness

# Check for leftover old patterns
rp-cli -e 'search "oldPattern|deprecatedAPI"'

# Verify new patterns in use
rp-cli -e 'search "newPattern|currentAPI"'

# Check version numbers
cat package.json pyproject.toml | grep -E "version|\"name\""

# Look for TODO/migration markers
rp-cli -e 'search "TODO.*migration|FIXME.*upgrade"'

Step 3: Review Checklist

Completeness

  • All old patterns replaced
  • No deprecated APIs in use
  • Dependencies updated
  • No partial migrations

Compatibility

  • Backward compatible (if required)
  • Deprecation warnings addressed
  • Data migrations complete

Safety

  • Tests pass on new version
  • No regressions
  • Rollback plan exists
  • Monitoring in place

Consistency

  • No mixed old/new patterns
  • Documentation updated
  • Changelog updated

Step 4: Write Output

ALWAYS write review to:

$CLAUDE_PROJECT_DIR/.claude/cache/agents/surveyor/output-{timestamp}.md

Output Format

# Migration Review: [From] -> [To]
Generated: [timestamp]
Reviewer: surveyor-agent

## Verdict: COMPLETE / INCOMPLETE / BLOCKED

## Summary
**Migration Scope:** [Framework/Library/Infrastructure]
**Completeness:** X% complete
**Blocking Issues:** [count]

## Version Verification

| Component | Expected | Actual | Status |
|-----------|----------|--------|--------|
| framework | 2.0.0 | 2.0.0 | OK |
| library-a | 3.0.0 | 2.5.0 | OUTDATED |

## Completeness Check

### Old Patterns Found (Should be zero)
| Pattern | Occurrences | Locations |
|---------|-------------|-----------|
| oldFunction() | 3 | file1.ts, file2.ts |
| deprecatedClass | 0 | - |

### New Patterns Adopted
| Pattern | Occurrences | Expected |
|---------|-------------|----------|
| newFunction() | 15 | 15 |
| currentClass | 8 | 8 |

## Leftover Migration Tasks

### Incomplete
- [ ] `src/legacy/old-module.ts` - Still uses old API
- [ ] `src/utils/helper.ts:45` - Deprecated function call

### Skipped (with justification)
- [ ] `src/vendor/third-party.ts` - External code, out of scope

## Dependency Audit

| Dependency | Pre-Migration | Post-Migration | Compatible |
|------------|---------------|----------------|------------|
| dep-a | 1.0.0 | 2.0.0 | Yes |
| dep-b | 3.0.0 | 3.0.0 | Yes |

## Breaking Changes Addressed

| Breaking Change | Status | Notes |
|-----------------|--------|-------|
| API signature change | Fixed | All callers updated |
| Default behavior change | Tested | Works as expected |

## Test Results

### Test Suite Status
- Unit tests: PASS / FAIL
- Integration tests: PASS / FAIL
- E2E tests: PASS / FAIL

### Migration-Specific Tests
- [ ] Tests for new API patterns
- [ ] Tests for data migrations
- [ ] Regression tests

## Data Migration Status (if applicable)

| Data Source | Records | Migrated | Verified |
|-------------|---------|----------|----------|
| users table | 1000 | 1000 | Yes |
| orders table | 5000 | 5000 | Yes |

## Rollback Readiness

**Rollback Possible:** Yes / No
**Rollback Tested:** Yes / No
**Rollback Steps Documented:** Yes / No

### Rollback Risks
- [Risk if rollback needed]

## Issues

### Critical (Blocks Completion)
**Issue:** [Incomplete migration]
**Location:** `file.ts:45`
**Required Action:** [What must be done]

### Warnings
**Issue:** [Potential concern]
**Recommendation:** [What to monitor]

## Recommendations

### Before Declaring Complete
1. [Required action]
2. [Required action]

### Post-Migration Tasks
1. [Remove deprecated code in next release]
2. [Update monitoring dashboards]

Read the full file on GitHub · 202 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. 8d ago First seen · 202 lines · 7 tokens per session scan A 3cd205ae3ef8

Subscribe to this mod's changes

surveyor is an agent published in the GitHub repository parcadei/Continuous-Claude-v3 (3,937 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,237 once invoked, about $0.0000 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.

Related

Other agents, from other repositories

flutter-reviewer

Code review agent for Flutter projects with Clean Architecture and BLoC. Validates architecture compliance, type safety, @freezed usage. AUTO-FIX: fixes all issues found.

aleksandr-chaika/flutter-clean-arch-skills · 40 tokens

code-reviewer

Dedicated read-only code review specialist. Use for /code-review after the review mode and target are resolved.

Byunk/minimal-claude-code · 25 tokens

fizzy-tasks

Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.

keskinonur/claude-plugin-fizzy · 39 tokens

shadow-auditor

Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.

AgentWorkforce/relay · 27 tokens

geo-routing-engineer

Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…

avelikiy/great_cto · 112 tokens

architecture-reviewer

Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.

FlorianBruniaux/claude-code-plugins · 45 tokens