Migrating Claude Agent SDK To Pydantic AI
pydantic/pydantic-ai
Migrate Python applications from the Claude Agent SDK to Pydantic AI and, only when needed, Pydantic AI Harness.
This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop"…
Install Smart Ralph
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tzachbon/smart-ralph smart-ralph --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .claude/skills/smart-ralph && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .claude/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralphType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tzachbon/smart-ralph smart-ralph --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .agents/skills/smart-ralph && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .agents/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tzachbon/smart-ralph smart-ralph --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .cursor/skills/smart-ralph && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .cursor/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tzachbon/smart-ralph.git --path plugins/ralph-specum/skills/smart-ralph--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tzachbon/smart-ralph smart-ralph --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .gemini/skills/smart-ralph && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .gemini/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tzachbon/smart-ralph smart-ralphInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .github/skills/smart-ralph && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .github/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tzachbon/smart-ralph --skill smart-ralph -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tzachbon/smart-ralph smart-ralph --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tzachbon/smart-ralph.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ralph-specum/skills/smart-ralph .opencode/skills/smart-ralph && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "smart-ralph" agent skill from https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-specum/skills/smart-ralph into .opencode/skills/smart-ralph/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "smart-ralph", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
smart-ralph- GitHub stars
- 558
- Token cost
- ~2k tokens
- SKILL.md length
- 922 words
- Files
- 2 (incl. references)
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop"…
- Works in 3 steps: Stage spec/feature files after generation → Commit with message: chore(): commit… → Keep the commit local unless a separate…
- Asks about ralph arguments
- SKILL.md covers Common Arguments, Execution Modes, State File and Commit Behavior, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Smart Ralph is an agent skill from tzachbon/smart-ralph. This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all Ralph Specum operations.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/state-file-schema.md`).
It sits in Agent Workflows, covering Subagents, Autonomous loops and State management. The repository describes itself as: Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow. The licence is MIT.
When your agent uses it
- Asks about ralph arguments
- Ralph state file
- Prototype overlay
- Execution modes
Example prompts
- “ralph arguments”
- “quick mode”
- “commit spec”
- “/smart-ralph”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Stage spec/feature files after generation
- Commit with message: chore(): commit spec files before implementation
- Keep the commit local unless a separate command and explicit authority permit a remote action
What it can do on your machine
Read from SKILL.md and the folder at commit ac7251a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Smart Ralph loads about 2k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 922 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from tzachbon/smart-ralph at commit ac7251a, republished under its MIT licence (© tzachbon). 922 words, ~1,955 tokens.
Download SKILL.mdSave it as
.claude/skills/smart-ralph/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- smart-ralph
- description
- This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all Ralph Specum operations.
- version
- 0.2.0
- user-invocable
- false
Smart Ralph
Core skill for all Ralph plugins. Defines common arguments, execution modes, shared behaviors, and coordinator delegation rules.
Common Arguments
All Ralph commands support these standard arguments:
| Argument | Short | Description | Default |
|---|---|---|---|
--quick | Exact token that enables persistent non-interactive generation | false | |
--interactive | Exact token that clears persistent quick mode | - | |
--commit | -c | Commit spec/feature files locally after generation | true (normal), false (quick) |
--no-commit | Explicitly disable committing files | - | |
--max-task-iterations | -m | Max retries per failed task before stopping | 5 |
--fresh | -f | Force new spec/feature, overwrite if exists | false |
Argument precedence: --no-commit > --commit > mode default.
Execution Modes
Normal Mode (Interactive)
- Exact
--interactiveclears a prior authorized quick mode - No mode flag resets legacy quick state that lacks exact
--quickauthorization - User reviews artifacts between phases
- Phase transitions require explicit commands
- Each phase sets
awaitingApproval: true - Commits spec files by default
- Research and requirements may offer the optional prototype overlay
- The user owns prototype capture, verdict, handoff, and deletion decisions
Quick Mode (--quick)
- Only an exact
--quickargument token enables this mode -q, settings defaults, substrings, and natural-language requests do not enable it--quickwith--interactiveis an error- Skip all interactive prompts, interviews, and approval pauses
- Run the same phase agents (research, requirements, design, tasks) sequentially
- Agents receive a "be more opinionated" directive since there is no user feedback
- spec-reviewer validates each artifact (max 3 iterations)
- Run at most one agent-owned prototype request after requirements and before design
- Take over the oldest design-blocking prototype when one exists; otherwise choose the highest-risk grounded question
- Ask no prototype question or decision and continue to design after every outcome
- Immediately start execution after all phases complete
- Do NOT commit by default (use
--committo override) - Still delegate to subagents (delegation is mandatory)
State File
All Ralph plugins use .ralph-state.json for execution state. See references/state-file-schema.md for full schema.
Key fields: phase, taskIndex, totalTasks, taskIteration, maxTaskIterations, awaitingApproval, quickMode, quickAuthorization, phaseSkillLoad, phaseInterview, and optional activePrototypes.
Prototype is an overlay. phase remains one of the five main workflow phases and is never prototype. Resolve basePath before access, treat a missing activePrototypes map as empty, and route every mutation or deletion through hooks/scripts/locked-state.py. Read references/state-file-schema.md before changing state, resuming an overlay, or deciding whether execution state may be deleted.
Commit Behavior
When commitSpec is true:
- Stage spec/feature files after generation
- Commit with message:
chore(<plugin>): commit spec files before implementation - Keep the commit local unless a separate command and explicit authority permit a remote action
When commitSpec is false:
- Files remain uncommitted
- User can manually commit later
Prototype terminal records are spec artifacts, so commitSpec controls their local commit. Retained prototype source always receives a local commit on its isolated branch, independent of commitSpec. Neither path authorizes a push, remote branch, PR inclusion, issue mutation, or ticket comment.
Show full SKILL.md (464 more words)Show less
Prototype Overlay
The coordinator follows this sequence:
- Resolve
basePath, reconcile candidates and finals, and reserve or resumeactivePrototypes.<id>under the state lock. Completion criterion: the main phase and unrelated fields are unchanged. - Keep source in an isolated sibling worktree or eligible scratch path. Completion criterion: the current checkout remains on its original branch and prototype files exist only in the recorded isolation path.
- Build and review one falsifiable question. Completion criterion: the reviewer passes the exact candidate bytes, source/run evidence, isolation, blocker, handoff, and
sourceDisposition. - Publish one immutable terminal record without overwrite, apply gate selection, restore the recorded return phase/task, then remove the active entry under lock. Completion criterion: downstream work sees only valid, non-superseded, gate-approved evidence.
Normal mode waits without a verdict or handoff timeout and keeps decisions with the user. Quick mode owns the one post-requirements request, can take over the oldest design blocker, uses reviewed receipts for eligible ephemeral cleanup, and always continues to design. Cancellation and interruption preserve source and publish reviewed terminal evidence before active-state removal.
Prototype source, records, cleanup receipts, and quarantines are local evidence. A remote push, branch publication, PR inclusion, issue write, or deletion outside the single quick ephemeral cleanup path requires separate explicit authority.
Task Execution Loop
Ralph Specum v3.0.0+ has a self-contained execution loop via the stop-hook. No external dependencies required.
Key signals:
TASK_COMPLETE- executor finished taskALL_TASKS_COMPLETE- coordinator ends loop
Error Handling
When taskIteration > maxTaskIterations: block task, suggest manual intervention.
If state file missing/invalid: output error, suggest re-running implement command.
Branch Management
All Ralph plugins follow consistent branch strategy:
- Check current branch before starting
- If on default branch (main/master): prompt for branch strategy
- If on feature branch: offer to continue or create new
- Exact
--quick: create a feature branch without prompting only when currently on the default branch; otherwise keep the current non-default branch. LegacyquickMode: truedoes not select this path.
Prototype isolation is separate from this feature-branch choice. Create or reuse a sibling worktree or eligible scratch path without checking out its branch in the current checkout. Retained and interrupted source remains available for recovery.
Coordinator Behavior
The main agent is a coordinator, not an implementer. Delegate all work to subagents.
Coordinator Responsibilities
- Parse user input and determine intent
- Read state files for context
- Delegate work to subagents via Task tool
- Report results to user
Do Not
- Write code, create files, or modify source directly
- Run implementation commands (npm, git commit, file edits)
- Perform research, analysis, or design directly
- Execute task steps from tasks.md
Delegation Mapping
| Work Type | Delegate To |
|---|---|
| Research | Research Team (parallel teammates) |
| Requirements | product-manager subagent |
| Design | architect-reviewer subagent |
| Task planning | task-planner subagent |
| Task execution | spec-executor subagent |
| Prototype building | prototype-builder background subagent |
Quick mode still requires delegation.
© tzachbon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in plugins/ralph-specum/skills/smart-ralph of tzachbon/smart-ralph.
- SKILL.md
- references/state-file-schema.md
Open the folder on GitHubat commit ac7251a
Compare with similar skills
Smart Ralph next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Smart Ralph this skilltzachbon/smart-ralph | 558 | — | ~2k | Automated safety check: Pass | MIT | |
| Migrating Claude Agent SDK To Pydantic AIpydantic/pydantic-ai | 20k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Cursor Orchestratecursor/plugins | 10k | — | ~1.1k | Automated safety check: Pass | None | |
| Agent-Foreman Feature Runmylukin/agent-foreman | 250 | — | ~1.6k | Automated safety check: Notes | None | |
| Spec-Driven Development v2LichAmnesia/lich-skills | 234 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Optimizeevo-hq/evo | 1.5k | — | ~13k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Cursor Orchestrate
cursor/plugins
Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.
Agent-Foreman Feature Run
mylukin/agent-foreman
Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.
Spec-Driven Development v2
LichAmnesia/lich-skills
Organizes long-running agent work into a Project, Sprint and Task hierarchy with per-task state files, isolated worktrees, review loops and script-checked rules.
Optimize
evo-hq/evo
Drive structured autoresearch iteration after evo:discover and the baseline commit.
Babysitter Process Runner
a5c-ai/babysitter
Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called…
More from tzachbon/smart-ralph
All 26 skills in this repoCommunication Style
tzachbon/smart-ralph
This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs…
Interview Framework
tzachbon/smart-ralph
This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview…
Reality Verification
tzachbon/smart-ralph
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only…
Spec Workflow
tzachbon/smart-ralph
This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks"…
Ralph Specum Design
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use $ralph-specum-design, or explicitly asks Ralph Specum in Codex to run the design phase.
Ralph Specum Tasks
tzachbon/smart-ralph
This skill should be used only when the user explicitly asks to use $ralph-specum-tasks, or explicitly asks Ralph Specum in Codex to run the tasks phase.
Related
Categories
Questions about Smart Ralph
What does Smart Ralph do?
This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop"…. Smart Ralph is an agent skill from tzachbon/smart-ralph. This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior.
When should I use Smart Ralph?
Smart Ralph fits situations like: asks about ralph arguments; ralph state file; prototype overlay; execution modes.
How do I install Smart Ralph in Claude Code?
Run `npx skills add tzachbon/smart-ralph --skill smart-ralph -a claude-code`. Or copy the skill folder (plugins/ralph-specum/skills/smart-ralph in tzachbon/smart-ralph) into .claude/skills/smart-ralph in your project. Claude Code loads it when a task matches its description.
How do I install Smart Ralph in Codex?
Run `npx skills add tzachbon/smart-ralph --skill smart-ralph -a codex`. Or copy the skill folder (plugins/ralph-specum/skills/smart-ralph in tzachbon/smart-ralph) into .agents/skills/smart-ralph in your project. Codex loads it when a task matches its description.
Can I use Smart Ralph in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tzachbon/smart-ralph --skill smart-ralph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/smart-ralph, .gemini/skills/smart-ralph, .github/skills/smart-ralph and .opencode/skills/smart-ralph in your project.
What does Smart Ralph need to run?
SKILL.md names no scripts, command-line tools or credentials: Smart Ralph is instructions for the agent only.
Does Smart Ralph access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Smart Ralph safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Smart Ralph use?
Smart Ralph is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Smart Ralph use?
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Smart Ralph?
Skills that share tags, products or a category with Smart Ralph: Migrating Claude Agent SDK To Pydantic AI (pydantic/pydantic-ai, 20k stars), Cursor Orchestrate (cursor/plugins, 10k stars), Agent-Foreman Feature Run (mylukin/agent-foreman, 250 stars) and Spec-Driven Development v2 (LichAmnesia/lich-skills, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Smart Ralph?
tzachbon (a GitHub user) maintains it in tzachbon/smart-ralph, which has 558 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on September 16, 2026.
Source: tzachbon/smart-ralph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.