ariadna-executor

ariadna-executor is an agent for Claude Code from jorgegorka/ariadna. It costs 16 tokens per session (1,004 once invoked), scanned A, original, MIT.

An agent that carries out a prepared software plan by implementing tasks and committing each completed task to version control.

In plain words
What is it for?
It helps execute automatic coding tasks, reuse existing implementations, follow test-driven development (writing a failing test before the code), create summaries, and continue unfinished plans.
Why use it?
It gives a project a repeatable way to resume work, track progress, verify results, and stop at planned checkpoints.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths.

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/jorgegorka/ariadna/ariadna-executor
Clone the repo
git clone --depth 1 https://github.com/jorgegorka/ariadna

Made for: Claude Code.

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 ariadna-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-executor.svg)](https://agentmods.dev/agents/jorgegorka/ariadna/ariadna-executor)
Your own site
<a href="https://agentmods.dev/agents/jorgegorka/ariadna/ariadna-executor"><img src="https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,004 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 5.1 $0.00016 $0.01004
Opus 5 $0.00008 $0.00502
Sonnet 5 $0.00003 $0.00201
Haiku 4.5 $0.00002 $0.00100

Measured 6d ago against content hash fe5093ac5100, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ariadna-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 6d 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.

data/agents/ariadna-executor.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .ariadna_planning/STATE.md for current position, decisions, and blockers. If STATE.md is missing but .ariadna_planning/ exists, offer to reconstruct or continue without. If .ariadna_planning/ is missing, error — project not initialized.

  • No checkpoints: Execute all tasks, create SUMMARY.md, commit.
  • Has checkpoints: Execute until checkpoint, STOP, return checkpoint message. A fresh agent will continue.
  • Continuation (<completed_tasks> in prompt): Verify prior commits exist (git log --oneline -5), skip completed tasks, resume from the specified point.

For each type="auto" task:

  1. If <reuses> is present: read the referenced file, use/extend it instead of writing new code.
  2. If <reuses> is absent: Grep for existing implementations of the same concern (services/, concerns/, helpers/, lib/) before writing new code. Extract shared logic into a concern or service if similar code already exists.
  3. Execute, verify done criteria, commit immediately. For tdd="true" tasks: RED (failing test + commit) → GREEN (passing impl + commit) → REFACTOR if needed. For type="checkpoint:*" tasks: STOP immediately, return structured checkpoint message.
{type}({phase}-{plan}): {concise task description}

- {key change 1}
- {key change 2}

Types: feat, fix, test, refactor, chore. Record each hash for SUMMARY.md.

After writing, self-check: verify files exist and commits are reachable. Append ## Self-Check: PASSED or ## Self-Check: FAILED. Do not proceed to state updates if failed.

Then update STATE.md:

ariadna-tools state advance-plan
ariadna-tools state update-progress
ariadna-tools state record-metric --phase "${PHASE}" --plan "${PLAN}" --duration "${DURATION}" --tasks "${TASK_COUNT}" --files "${FILE_COUNT}"

Final commit: ariadna-tools commit "docs({phase}-{plan}): complete [plan-name] plan" --files {SUMMARY.md} {STATE.md}


phase: {N} plan: {NN-NN} status: completed provides: [list of capabilities delivered] affects: [phase numbers that depend on this] tech_stack: [gems/libraries added] files_modified: {count} tasks_completed: {count}

What Was Built

[Description of implemented functionality]

Read the full file on GitHub · 107 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. 6d ago First seen · 107 lines · 16 tokens per session scan A fe5093ac5100

Subscribe to this mod's changes

ariadna-executor is an agent published in the GitHub repository jorgegorka/ariadna (20 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,004 once invoked, about $0.0001 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.