Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Details behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify…
Install Run Local Model
$ npx skills add autonomous-ai/openharness --skill run-local-model -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness run-local-model --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .claude/skills/run-local-model && 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 "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .claude/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-modelType 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 autonomous-ai/openharness --skill run-local-model -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness run-local-model --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .agents/skills/run-local-model && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .agents/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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 autonomous-ai/openharness --skill run-local-model -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness run-local-model --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .cursor/skills/run-local-model && 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 "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .cursor/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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/autonomous-ai/openharness.git --path store/agents/autonomous-grid/skills/run-local-model--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 autonomous-ai/openharness --skill run-local-model -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness run-local-model --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .gemini/skills/run-local-model && 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 "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .gemini/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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 autonomous-ai/openharness run-local-modelInstalls 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 autonomous-ai/openharness --skill run-local-model -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .github/skills/run-local-model && 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 "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .github/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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 autonomous-ai/openharness --skill run-local-model -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness run-local-model --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/autonomous-grid/skills/run-local-model .opencode/skills/run-local-model && 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 "run-local-model" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/autonomous-grid/skills/run-local-model into .opencode/skills/run-local-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-local-model", 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
run-local-model- GitHub stars
- 1.1k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 1,028 words
- Files
- 1
- Skills in repo
- 100
- Repo updated
- First seen
- Licence
- MIT
At a glance
Details behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify…
- Works in 4 steps: "$GRID_FLEET" recipe vllm|sglang… → "$GRID_FLEET" model-facts ORG/NAME|DIR —… → Agent indexes: docs.ollama.com/llms.txt, → …
- Tasks that involve Agent instruction files
- SKILL.md covers Purpose → settings (the only…, Reading fleet models, Size and Choose the file, then the engine, plus 4 more sections
- Calls ollama
What it does
Run Local Model is an agent skill from autonomous-ai/openharness. Details behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify checks, and where to read when unsure. Open it when a step of that flow needs more than the flow says.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
When your agent uses it
- Tasks that involve Agent instruction files
Example prompts
- “Starting a model on this computer”
- “Use the run-local-model skill to detail behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing…”
- “/run-local-model”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- "$GRID_FLEET" recipe vllm|sglang ORG/NAME — the official recipe for that exact model (exit 3: none).
- "$GRID_FLEET" model-facts ORG/NAME|DIR — architecture, context, sampling defaults, the template's
- Agent indexes: docs.ollama.com/llms.txt,
- Nothing says it: tell the person this model cannot be set up reliably here and offer the next one.
What it can do on your machine
Read from SKILL.md and the folder at commit 50da5db. 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
Shell commands in SKILL.md call:
ollama
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
recipes.vllm.aidocs.ollama.comlmstudio.aidocs.sglang.io
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
Run Local Model loads about 1.8k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 1,028 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 autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 1,028 words, ~1,807 tokens.
Download SKILL.mdSave it as
.claude/skills/run-local-model/SKILL.md (or your agent's skills folder).- name
- run-local-model
- description
- Details behind AGENTS.md's 'Starting a model on this computer' flow: reading `fleet models`, sizing a start, choosing file and engine, picking a model for an engine with none, what `fleet verify` checks, and where to read when unsure. Open it when a step of that flow needs more than the flow says.
Run a local model — details
The flow itself is in AGENTS.md. Tags: [run] seen on a real machine (M1 Pro 32 GB, macOS 26.6,
2026-09-29), [doc] official docs (see the engine-* skill), [code] read in the tool's source.
Purpose → settings (the only thing asked)
Coding · Chat and writing · Reading images · Just something fast. Context is never below 64K: every model here is used by an agent whose own prompt fills a small window; Ollama's docs set the same floor for agents [doc]. When 64K does not fit, take a smaller model, never a smaller window.
| Purpose | Context | At once | Also needs |
|---|---|---|---|
| Coding | 128K when it fits, else 64K | 1 | tool calls |
| Chat and writing, or fast | 64K | 1 | — |
| Reading images | 64K | 1 | a projector beside the file |
Thinking is off for everyday use.
Reading fleet models
machine.accelerators[]: a GPU counts only withactive: true(its own tool answered).active: falsecomes with anerror(e.g. no driver): say it in one line; plan no GPU engine on it.machine.engines[]: installed engines, running or not.machine.canRun: the kinds this hardware can run at all — never propose one outside it.machine.memory.availableBytes,swapUsedBytes: room right now. Metal anddevice-infodo not see other apps (Metal said 25 GiB free while macOS was 11 GB into swap [run]).machine.accelerators[].totalBytes: the GPU ceiling, below total RAM on a Mac — read it here, never assume it;device-inforeports a different figure there [run] — use the smaller.engines[]: answering engines and their exact--atURL.openai-compatiblewhose "models" are not models is another app: leave it alone.models[]: one entry per real file (alsoAt= other apps holding the same file), withformat,bytes,projector, and for GGUFcontextLength,kvBytesPerToken,toolCalls,unsupportedTensorTypes.
Size
need = weights + context × kvBytesPerToken × slots + 0.5 GB (+ projector when vision is on)kvBytesPerToken matched what llama.cpp allocated exactly [run]; files of similar size needed from
20 KiB to 160 KiB per token, so never skip this. Null (latent attention): start at 64K and read the
engine's memory report. Fits when need ≤ availableBytes + 3 GB and ≤ the GPU ceiling (macOS moves
idle pages to swap once; swap still climbing a minute after start means too big). Too big: a smaller
file, or ask the one trade-off — "close other apps first, or a lighter model beside your work?".
Choose the file, then the engine
Drop: unsupportedTensorTypes not empty (llama.cpp refuses them [run]); context below 64K; no tool
calls for coding; no projector for images; anything that does not fit. Prefer newer families, more
parameters at 4-bit over fewer at 8-bit, and mixture-of-experts models when memory allows.
| The file | Mac (Apple silicon) | Linux + active NVIDIA/AMD GPU | CPU only |
|---|---|---|---|
| served by an engine already answering | join --at URL/v1 -m ID --advertise-as ALIAS | same | same |
| GGUF from any app | Grid's engine (link into ~/.grid/models) | same | same |
| MLX folder | mlx-lm (engine-mlx-lm) | — | — |
| Hugging Face safetensors | mlx-lm | vLLM or SGLang from the model's recipe | find a GGUF |
Grid only serves from ~/.grid/models: its launcher keeps just the file name of --serve and looks
there; a projector must sit beside it [code: grid shared/engine/launcher.py]. A symlink costs no disk.
Never ollama create to reuse a file (it copies it [run]); never vLLM or SGLang on a Mac (CPU-only /
no macOS build [run]); never download a second copy only to switch engines. On Apple silicon, when a
new download is needed and mlx-lm or LM Studio is installed, an MLX build is sound — Ollama itself
moved its Apple engine to MLX [doc: ollama.com/blog/mlx].
On Apple silicon with mlx-lm (or LM Studio) installed, MLX first: when the same model exists as an
MLX folder and as a GGUF and the MLX one fits, serve the MLX one. The choice is still model-first —
never a bigger MLX model that does not fit over a smaller GGUF that does. The report names what was
passed over and why, one line each ("<model> (<format>): needs <N> GB, <M> GB free"), so "why not MLX?"
is answered before anyone asks.
Show full SKILL.md (368 more words)Show less
An engine installed, nothing to serve
Offer 2–3 that fit (plain name, GB, what it is good at) plus "none of these"; the download waits for the go-ahead.
- Mac with mlx-lm or LM Studio:
"$GRID_FLEET" candidates mlx [--search WORDS] [--sort downloads|trending|recent]— mlx-community models sized from their real files, cache at 64K,fitsagainst the GPU ceiling. - Linux GPU with vLLM or SGLang: pick families from recipes.vllm.ai/llms.txt
or the SGLang cookbook, then
fleet recipeeach;vramMinimumGbagainst the GPU decides. - Grid's engine or Ollama with nothing: Grid's catalog (
grid-operationsstep 4), pulled into Grid. - The person names an engine outside
canRun: say why in one line (no active GPU, not a Mac).
This computer already on that grid
In remote mode a computer joins a grid as one identity, and Grid's --serve engine cannot share it: a
second model is refused with "can't join a multi-engine identity. Run grid leave, then re-join every
engine as external --at <url> -m <model>" [run]. Ask Replace X with Y · Keep X; never leave an
engine the person did not agree to.
What fleet verify checks
Engine: ready (/models within 180 s, every 3 s), listed, answer (max_tokens 16, thinking off;
reasoning-only output fails), tool call (read_file must come back as tool_calls), speed. With
--grid: relay listed (every 10 s up to 300 s) and relay answer (up to 420 s, a "still waiting"
line every 15 s). Exit 0 only when all pass. Seen end to end: an mlx-lm engine joined a local grid with
--at …/v1 in 6 s and passed all seven in 10 s; a Grid-engine GGUF passed at 19 tok/s [run].
When unsure: read, never guess
"$GRID_FLEET" recipe vllm|sglang ORG/NAME— the official recipe for that exact model (exit 3: none)."$GRID_FLEET" model-facts ORG/NAME|DIR— architecture, context, sampling defaults, the template's tool-call syntax, the authors' serve commands, and whether each engine lists the architecture (listed: null= cannot tell).- Agent indexes: docs.ollama.com/llms.txt, lmstudio.ai/llms.txt, recipes.vllm.ai/llms.txt, docs.sglang.io/llms.txt; vLLM and mlx-lm docs as raw markdown on GitHub.
- Nothing says it: tell the person this model cannot be set up reliably here and offer the next one.
fleet models reads this computer only; a Harness-linked machine's disk is not visible yet.
© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in store/agents/autonomous-grid/skills/run-local-model of autonomous-ai/openharness.
Open the folder on GitHubat commit 50da5db
Compare with similar skills
Run Local Model 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 |
|---|---|---|---|---|---|---|
| Run Local Model this skillautonomous-ai/openharness | 1.1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 103k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Claude ReflectBayramAnnakov/claude-reflect | 1.7k | 2 repos | ~627 | Automated safety check: Pass | MIT | |
| Writing For Agentsbestofjs/bestofjs | 3.1k | 19 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
Claude Reflect
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Writing For Agents
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
More from autonomous-ai/openharness
All 100 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Related
Categories
Questions about Run Local Model
What does Run Local Model do?
Details behind AGENTS.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify…. Run Local Model is an agent skill from autonomous-ai/openharness.md's 'Starting a model on this computer' flow: reading fleet models, sizing a start, choosing file and engine, picking a model for an engine with none, what fleet verify checks, and where to read when unsure.
When should I use Run Local Model?
Run Local Model fits situations like: tasks that involve Agent instruction files.
How do I install Run Local Model in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill run-local-model -a claude-code`. Or copy the skill folder (store/agents/autonomous-grid/skills/run-local-model in autonomous-ai/openharness) into .claude/skills/run-local-model in your project. Claude Code loads it when a task matches its description.
How do I install Run Local Model in Codex?
Run `npx skills add autonomous-ai/openharness --skill run-local-model -a codex`. Or copy the skill folder (store/agents/autonomous-grid/skills/run-local-model in autonomous-ai/openharness) into .agents/skills/run-local-model in your project. Codex loads it when a task matches its description.
Can I use Run Local Model 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 autonomous-ai/openharness --skill run-local-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/run-local-model, .gemini/skills/run-local-model, .github/skills/run-local-model and .opencode/skills/run-local-model in your project.
What does Run Local Model need to run?
Going by SKILL.md and its folder, Run Local Model needs the command-line tools its instructions call (ollama).
Does Run Local Model access the network?
SKILL.md names 4 domains. As links in the text: recipes.vllm.ai, docs.ollama.com, lmstudio.ai and docs.sglang.io. This is read from the text; nothing was executed.
Is Run Local Model 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 Run Local Model use?
Run Local Model 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 Run Local Model use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Run Local Model?
Skills that share tags, products or a category with Run Local Model: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Run Local Model?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.