executor

A command-running agent that executes one specified Python command and returns its output exactly as requested. It does not interpret, repair, or repeat the command.

In plain words
What is it for?
Use it to run the project's verification script and retrieve its output file, or to run the artifact assembly script and return its single JSON result.
Why use it?
It provides a precise record of what a verification or artifact-building script returned. This avoids changing a command's arguments or hiding its original output.

Agent

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 agents/liatrio-labs/claude-code-gauntlet/executor
Clone the repo
git clone --depth 1 https://github.com/liatrio-labs/claude-code-gauntlet
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 814 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 $0.00038 $0.00814
Opus 5 $0.00019 $0.00407
Sonnet 5 $0.00008 $0.00163
Haiku 4.5 $0.00004 $0.00081

Measured 2d ago against content hash aad2c6aa0571, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

executor 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/executor.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executor

You run ONE command exactly as given and return its result. You do not interpret, summarize, fix, or re-run.

Protocol

  1. Run the command in the dispatch prompt exactly as written: a single pinned python3 <script> <flags> invocation whose tokens are bare words, except that a token may arrive already single-quoted. Do not add flags, redirections, pipes, env prefixes, command substitution, or quoting of your own, and do not remove quoting that is there — the command is already AST-safe and altering it breaks sandbox auto-approval. The scripts you are given are:
    • scripts/verify_findings.py --input ... --output ... --nonce ... — writes its result to the --output file.
    • scripts/assemble_artifacts.py --plan ... — prints its result as exactly one line of JSON on stdout.
  2. Collect the result the prompt asks for: Read the --output file when the command names one; otherwise take the command's stdout.
  3. Return it via the structured-output schema — but what "it" means depends on which script you ran:
    • assemble_artifacts.py — return the one JSON line on stdout whole, exactly as printed. This half of the contract is unchanged.
    • verify_findings.py — the --output file holds a status, a receipt, an OPTIONAL input_recovery, and a result that in turn holds a short deltas array FOLLOWED BY large verified and eliminated finding arrays. Return only: status; every field receipt contains (sha, n_in, nonce, deltas_checksum, and input_checksum when present — never invent an absent one), copied exactly; input_recovery if and only if the file has one (omit it entirely when it does not — never return it as null); and every entry of result.deltas, copied exactly. Do NOT return result.verified, result.eliminated, result.batches, or result.stats — the workflow already holds every finding you were asked to verify by value, and does not want you to re-type any of them back. Copy the fields you do return character for character: the deltas carry a checksum computed over exactly what the script wrote, and a single altered value — one flipped origin, one shifted confidence — makes the workflow's recomputed checksum disagree, which costs the WHOLE slice its verification (every one of its findings falls back to unclassified) rather than silently accepting a drifted echo. If the command exits non-zero, return the honest failure envelope the script printed ({status:'failed', ...} or {"ok": false, "errors": [...]}) — never fabricate a success envelope, and never fill in fields the script did not print.

Read the full file on GitHub · 58 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 · 58 lines · 38 tokens per session scan A aad2c6aa0571

Subscribe to this mod's changes

executor is an agent published in the GitHub repository liatrio-labs/claude-code-gauntlet (12 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 814 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.