revert

A command that returns a project to an earlier Git checkpoint, which is a saved version of the code, while reviewing why the newer changes failed.

In plain words
What is it for?
Use it to list checkpoints, preview a revert, return to the latest or a named checkpoint, or run the process without applying changes.
Why use it?
It makes reverting failed work more deliberate by showing affected files, reset tasks, and changes that would be lost before confirmation.

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/ddunnock/claude-plugins/revert
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 787 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 $0.00008 $0.00787
Opus 5 $0.00004 $0.00394
Sonnet 5 $0.00002 $0.00157
Haiku 4.5 $0.00001 $0.00079

Measured 2d ago against content hash fa24862f865f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

revert 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.

mcps/knowledge-mcp/.claude/commands/revert.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revert

Revert to a previous git checkpoint with failure analysis and artifact recommendations.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Usage

/revert                    # Revert to most recent checkpoint
/revert [checkpoint-tag]   # Revert to specific checkpoint
/revert --list             # List available checkpoints
/revert --dry-run          # Preview without executing

MANDATORY: Pre-Revert Hooks

Pre-Hook 1: List and Validate Checkpoints

# List speckit checkpoints
git tag -l "speckit-checkpoint-*" --sort=-creatordate

IF no checkpoints exist: Stop and inform user.

Pre-Hook 2: Show Revert Preview

Before reverting, show:

  • Files that will be reverted
  • Tasks that will be reset
  • Changes that will be lost

Get explicit confirmation before proceeding.


Revert Process

Step 1: Save Current State for Analysis

# Save diff for analysis
git diff HEAD [checkpoint] > .claude/.cache/failed-changes.diff

# Save commit log
git log --oneline [checkpoint]..HEAD > .claude/.cache/failed-commits.log

Step 2: Execute Revert

# Stash uncommitted changes
git stash push -m "speckit-pre-revert-$(date +%Y%m%d_%H%M%S)"

# Reset to checkpoint
git reset --hard [checkpoint]

MANDATORY: Post-Revert Failure Analysis

CRITICAL: Always analyze what went wrong after reverting.

Analysis Steps

  1. Examine the diff - What was changed?

  2. Identify failure category:

    • SPEC_GAP - Requirements unclear
    • APPROACH_WRONG - Need different architecture
    • DEPENDENCY_ISSUE - External problem
    • TEST_MISMATCH - Tests don't match reality
    • SCOPE_CREEP - Too much at once
    • KNOWLEDGE_GAP - Need more research
  3. Generate recommendations:

    • Spec clarifications needed?
    • Plan revisions required?
    • Task decomposition suggested?

Update Artifacts

  1. project-status.md - Log revert, add blocker
  2. tasks.md - Reset status, add failure notes
  3. Create failure report - speckit/failure-analysis-[date].md

Read the full file on GitHub · 148 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 · 148 lines · 8 tokens per session scan A fa24862f865f

Subscribe to this mod's changes

revert is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 787 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.