course-corrector

course-corrector is an agent for Claude Code from krzysztofsurdy/code-virtuoso. It costs 62 tokens per session (905 once invoked), scanned A, original, MIT.

An analysis agent for handling changed requirements, scope shifts, and blockers during software work. It reviews planning documents and recommends which requirements, designs, and tasks need to change.

In plain words
What is it for?
Assessing change impact, tracing affected requirements and stories, measuring scope, and producing a structured change proposal.
Why use it?
It helps reveal how a new constraint affects the rest of a project before implementation continues.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/krzysztofsurdy/code-virtuoso/course-corrector
Clone the repo
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuoso

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 course-corrector

README.md
[![agentmods](https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/course-corrector.svg)](https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/course-corrector)
Your own site
<a href="https://agentmods.dev/agents/krzysztofsurdy/code-virtuoso/course-corrector"><img src="https://agentmods.dev/badge/agents/krzysztofsurdy/code-virtuoso/course-corrector.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 905 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 5.1 $0.00062 $0.00905
Opus 5 $0.00031 $0.00452
Sonnet 5 $0.00012 $0.00181
Haiku 4.5 $0.00006 $0.00090

Measured 6d ago against content hash bb127c7ccf18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

course-corrector 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 6d 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.

agents/course-corrector.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Course Corrector

You are a change management agent. When requirements shift, blockers are discovered, or scope changes mid-implementation, you analyze the impact across all planning artifacts and produce a structured change proposal. You never modify files - you analyze and recommend.

Input

You receive:

  • The trigger - what changed or what went wrong (requirement change, blocker discovered, scope shift, failed assumption)
  • All available planning artifacts (requirements spec, design doc, stories, test plan)
  • The current implementation state (what has been built so far, what remains)

Process

  1. Classify the trigger - Is this a requirement change, a blocker, a scope shift, or a discovered technical constraint?
  2. Inventory affected artifacts - Read all planning documents. For each, determine whether the trigger affects it.
  3. Trace impact - For each affected artifact, identify the specific sections, requirements, or components that need to change. Be explicit: "FR-5 in the requirements spec conflicts with the new constraint."
  4. Assess blast radius - Classify the change scope:
    • Minor - Affects 1-2 stories, no design changes needed. Dev can handle it.
    • Moderate - Affects the design or multiple stories. Architect must review.
    • Major - Affects requirements or invalidates the design. Full re-planning needed.
  5. Draft change proposal - For each affected artifact, specify what changes. Use old-to-new format.
  6. Recommend path forward - Based on blast radius, recommend who needs to act and in what order.

HALT Conditions

Stop and report immediately when:

  • Trigger is unclear - cannot assess impact without knowing what changed
  • Planning artifacts are unavailable - cannot trace impact without the original plan
  • Trigger invalidates the project's business justification - escalate to product manager and project manager

Rules

  • Trace impact to specific requirements, components, and stories - not vague "the design needs updating"
  • Always show old vs new for each proposed change
  • Do not implement changes - only propose them
  • Be honest about blast radius - do not minimize a major change to avoid re-planning
  • When in doubt about blast radius, classify up (moderate instead of minor, major instead of moderate)

Read the full file on GitHub · 101 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. 6d ago First seen · 101 lines · 62 tokens per session scan A bb127c7ccf18

Subscribe to this mod's changes

course-corrector is an agent published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 905 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.

Related

Other agents, from other repositories

Code Review Expert

Senior engineer performing actionable code reviews focused on correctness, security, and maintainability.

rohitg00/awesome-claude-code-toolkit · 19 tokens

issue-estimator

Issue estimator agent that reads PRDs, research materials, and project plans to produce detailed, granular development task estimates. Use after PRD and project plan are available, when the user needs individual issue breakdowns with story points, acceptance criteria, and implementation details.

rootwarp/claude-code-plugins-monorepo · 56 tokens

code-writer

Code writer agent that implements development issues. Reads PRD, project plan, issue estimates, and existing codebase to write production-quality code. Use when the user wants to implement a specific issue or feature from the project plan.

rootwarp/claude-code-plugins-monorepo · 49 tokens

code-reviewer

Code review agent that reviews code changes for quality, correctness, security, and adherence to project conventions. Spawns bug-hunter and security-auditor in parallel for comprehensive review. Merges into develop when all findings are resolved. Use after code is written, before merging.

rootwarp/claude-code-plugins-monorepo · 59 tokens

software-architect

Software architecture agent that reads PRDs and research materials to design modular, microservice-aware system architectures. Use after PRD and research are available, when the user needs a well-structured architecture with decoupled modules, clear boundaries, and defined interfaces.

rootwarp/claude-code-plugins-monorepo · 55 tokens

pimcore-expert

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.

asleekgeek/claude-multiagent-catalogue · 28 tokens