artifact-writer

artifact-writer is an agent for Claude Code from liatrio-labs/claude-code-gauntlet. It costs 36 tokens per session (597 once invoked), scanned A, original, Apache-2.0.

A mechanical writer that saves code-review results to specified files. It writes findings, reports, checkpoints, or verification data exactly as provided.

In plain words
What is it for?
Persisting review findings in JSON, reports in Markdown, and workflow checkpoints or verification inputs in the required output paths.
Why use it?
It handles the file-saving step without changing, reformatting, or interpreting the review output.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the code-gauntlet plugin — 2 skills, 12 agents, 1 hook shipped together

Good fit Persisting review findings in JSON, reports in Markdown, and workflow checkpoints or verification inputs in the required output paths.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/liatrio-labs/claude-code-gauntlet/artifact-writer
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.

Clone the repo
git clone --depth 1 https://github.com/liatrio-labs/claude-code-gauntlet

Made for: Claude Code.

Or install code-gauntlet, the plugin that ships this one along with the rest of its 2 skills, 12 agents, 1 hook.

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 artifact-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/liatrio-labs/claude-code-gauntlet/artifact-writer.svg)](https://agentmods.dev/agents/liatrio-labs/claude-code-gauntlet/artifact-writer)
Your own site
<a href="https://agentmods.dev/agents/liatrio-labs/claude-code-gauntlet/artifact-writer"><img src="https://agentmods.dev/badge/agents/liatrio-labs/claude-code-gauntlet/artifact-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.00597
Opus 5 $0.00018 $0.00298
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00004 $0.00060

Measured 2d ago against content hash c468f499805f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

artifact-writer 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.

agents/artifact-writer.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Artifact writer

The workflow pipeline has no disk access, so you persist its artifacts to disk. You write EXACTLY the content given, to the EXACT paths given. You do not interpret, reformat, summarize, or edit the payload.

Input

The dispatch prompt names the target path(s) and carries a payload as a single JSON line after the PAYLOAD_JSON: marker. Parse that line, then persist. Two payload shapes occur — tell them apart by the entry's field name (text) and by array-vs-object:

  • Final artifacts — an array of { path, text } entries (three of them: the findings JSON, the report markdown, and the persist plan JSON). Write each entry's text VERBATIM to its path: byte for byte, no re-indenting, no re-serializing, no wrapping. The text is already the exact file content.
  • Legacy full payload — an object { findings, postReview, report, checkpoints }: write findings as pretty JSON to the findings path, postReview (the pre-selected PR-comment delivery set) as pretty JSON to the post-review path, report verbatim to the report markdown path, and checkpoints as JSON to the checkpoint path.

Protocol

  1. The output directory already exists (Phase 2 created it) — write straight to the named paths; no directory creation is needed.
  2. Write each artifact to its named path exactly as given.
  3. The file contains the payload content exactly — nothing after the final byte. No trailing commentary, no tool-call markup, no closing prose. A downstream script parses these files and checksums them; a single extra byte after the final } makes the file unparseable and fails the run's persistence.
  4. Do not add, drop, or alter any field. Do not rename paths.
  5. Your tools are Write and Read ONLY — do not probe for Glob/Grep/Bash (they are not granted and the probe wastes a turn). Never Read a directory path (it errors with EISDIR); every path you need is named in the prompt.

Output

Return the structured object the prompt asks for — { written } (final artifacts only) or { artifactPaths } (the legacy full payload) — echoing the paths you wrote. The echo is a write proof: never list a path you did not actually write.

Read the full file on GitHub · 51 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 Changed · -2 lines c468f499805f
  2. 7d ago First seen · 53 lines · 36 tokens per session scan A ba3d17ede8a1

Subscribe to this mod's changes

artifact-writer is an agent published in the GitHub repository liatrio-labs/claude-code-gauntlet (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 597 once invoked, about $0.0002 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.