correct-course

A command for handling a significant change in a software project by following a change checklist. It examines effects on planned work and drafts updates to project documents for review.

In plain words
What is it for?
Use it to analyze changes affecting epics, user stories, product requirements, architecture documents, or the minimum viable product, and to prepare a change proposal.
Why use it?
It helps teams understand the consequences of a change before adjusting scope, rolling work back, or replanning.

Command for Claude Code

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 commands/gonewx/tasksentinel/correct-course
Clone the repo
git clone --depth 1 https://github.com/gonewx/TaskSentinel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,479 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 $0.00000 $0.01479
Opus 5 $0.00000 $0.00740
Sonnet 5 $0.00000 $0.00296
Haiku 4.5 $0.00000 $0.00148

Measured 2d ago against content hash a7bb226fc91a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

correct-course 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 2d 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

3 near-identical copies found in the catalogue:

.claude/commands/BMad/tasks/correct-course.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/correct-course Task

When this command is used, execute the following task:

Correct Course Task

Purpose

  • Guide a structured response to a change trigger using the .bmad-core/checklists/change-checklist.
  • Analyze the impacts of the change on epics, project artifacts, and the MVP, guided by the checklist's structure.
  • Explore potential solutions (e.g., adjust scope, rollback elements, re-scope features) as prompted by the checklist.
  • Draft specific, actionable proposed updates to any affected project artifacts (e.g., epics, user stories, PRD sections, architecture document sections) based on the analysis.
  • Produce a consolidated "Sprint Change Proposal" document that contains the impact analysis and the clearly drafted proposed edits for user review and approval.
  • Ensure a clear handoff path if the nature of the changes necessitates fundamental replanning by other core agents (like PM or Architect).

Instructions

1. Initial Setup & Mode Selection

  • Acknowledge Task & Inputs:
    • Confirm with the user that the "Correct Course Task" (Change Navigation & Integration) is being initiated.
    • Verify the change trigger and ensure you have the user's initial explanation of the issue and its perceived impact.
    • Confirm access to all relevant project artifacts (e.g., PRD, Epics/Stories, Architecture Documents, UI/UX Specifications) and, critically, the .bmad-core/checklists/change-checklist.
  • Establish Interaction Mode:
    • Ask the user their preferred interaction mode for this task:
      • "Incrementally (Default & Recommended): Shall we work through the change-checklist section by section, discussing findings and collaboratively drafting proposed changes for each relevant part before moving to the next? This allows for detailed, step-by-step refinement."
      • "YOLO Mode (Batch Processing): Or, would you prefer I conduct a more batched analysis based on the checklist and then present a consolidated set of findings and proposed changes for a broader review? This can be quicker for initial assessment but might require more extensive review of the combined proposals."
    • Once the user chooses, confirm the selected mode and then inform the user: "We will now use the change-checklist to analyze the change and draft proposed updates. I will guide you through the checklist items based on our chosen interaction mode."

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 0 tokens per session scan A a7bb226fc91a

Subscribe to this mod's changes

correct-course is a command published in the GitHub repository gonewx/TaskSentinel (18 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,479 tokens. 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.