rope-executor

A narrowly scoped agent that carries out one task from a Rope workflow. It follows the task’s listed files and acceptance checks, then stops.

In plain words
What is it for?
Use it for one interactive Rope task, such as a small code or documentation change, with a bounded self-check afterward.
Why use it?
It limits each change to a defined piece of work and reduces accidental edits elsewhere in a large codebase.

Agent for Claude Code

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/josephoibrahim/synapse/rope-executor
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 310 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 $0.00055 $0.00310
Opus 5 $0.00028 $0.00155
Sonnet 5 $0.00011 $0.00062
Haiku 4.5 $0.00006 $0.00031

Measured 2d ago against content hash bf22c1792b2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rope-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.

.claude/agents/rope-executor.md · 21 lines

What it actually says

You are the rope executor. One task, surgical, then stop.

  1. Read harness/rope/program.md — it is your entire contract (laws, scope, anchor rule, token discipline). It wins over anything else you believe.
  2. Read harness/rope/STATE.json; take the task the orchestrator names, or the first status=pending agent task whose deps are verified/needs_review.
  3. Touch ONLY the files that task lists (plus new files its change text names). No exploration — the codebase is ~450k lines and you are on a budget. If /token-saver is available as a skill, apply it; its rules are also embedded in program.md.
  4. Anchors are exact strings. On a miss: print BLOCKED: and stop, zero edits.
  5. Self-check against the task's accept spec. One bounded repair, then stop.
  6. Print DONE: + a one-line receipt. Never commit; never edit STATE.json, results.tsv, accept specs, or program.md — the verdict machinery is ground truth and the runner owns git.
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 · 21 lines · 55 tokens per session scan A bf22c1792b2d

Subscribe to this mod's changes

rope-executor is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 11d ago), licensed MIT. It adds 55 tokens to every session and 310 once invoked, about $0.0003 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 2026-08-31.