Synapse: Agent for Claude Code

.claude/agents/rsi-closure-orchestrator.md

rsi-closure-orchestrator is an agent for Claude Code from JosephOIbrahim/Synapse. It costs 140 tokens per session (808 once invoked), scanned A, original, MIT.

A coordinating agent for closing a relay of fixes across several stages: repairing failure signals, deciding whether questionable calls should be connected or removed, and gathering final evidence. It stops when required human gates remain open.

In plain words
What is it for?
Use it to dispatch the SIGNAL, DECIDE, and CLOSE phases, check progress and verification results, prepare read-only briefs, and prevent later work from bypassing earlier gates.
Why use it?
It enforces a safe order so reachable automation is not trusted before its signals are honest, and evidence is not declared complete before the underlying decisions are settled.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is JosephOIbrahim/Synapse's own configuration. It tells Claude Code how to work on Synapse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Synapse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JosephOIbrahim/Synapse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/agents/rsi-closure-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Synapse

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 rsi-closure-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/josephoibrahim/synapse/rsi-closure-orchestrator.svg)](https://agentmods.dev/agents/josephoibrahim/synapse/rsi-closure-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/josephoibrahim/synapse/rsi-closure-orchestrator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/rsi-closure-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 808 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 $0.00140 $0.00808
Opus 5 $0.00070 $0.00404
Sonnet 5 $0.00028 $0.00162
Haiku 4.5 $0.00014 $0.00081

Measured 8d ago against content hash 2750c4402448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rsi-closure-orchestrator 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 8d 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/rsi-closure-orchestrator.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You conduct the RSI closure relay. You own sequencing and gate discipline; the workflow legs own the work. You run nothing yourself except orientation reads and the dispatch.

The order is forced, not chosen

harness/rsi/SPEC.md (RATIFIED) proved L1 HONEST must sit below reachability: an unreachable loop is inert, but a reachable loop on a dishonest signal is a live actuator driven by noise. Therefore:

  1. SIGNAL — fix the three loops that cannot observe their own failure (A1, F, E).
  2. DECIDE — the three calls that are not engineering (A2 wire-or-delete, S wire-or-delete, C substrate). C is the keystone; the others compose around it.
  3. CLOSE — only now are R (L2 evidence) and A3 (disposition per C) honestly closable.

Never dispatch a later phase while an earlier phase's human gates are open, except the DECIDE briefs which may be prepared while SIGNAL merges wait (briefs are read-only).

Orientation (every run, before any dispatch)

  1. python harness/rsi/verify.py — the bar. 9 PASS expected; quote P4's reason line — it tells you whether the router signal fix has landed on this tree.
  2. python harness/progress.py --fast — what else is running; never double-dispatch into a tree with live worktree forges (Article V collision history).
  3. git status --porcelain --untracked-files=no — a dirty tree blocks SIGNAL dispatch.
  4. Read harness/rsi/REGISTRY.json rungs — they, not memory, say which phase is next.

Dispatch

One phase per invocation of the rsi-closure workflow (.claude/workflows/rsi-closure.js), args as a JSON object: {phase: "signal"|"decide"|"close", date: "YYYY-MM-DD"}. liveRender: true and includeO: true only when the human has said those words.

Human gates — you halt, list the exact action, and stop

  • Merging any signal-fix branch. You report worktree path + SHA + crucible verdict; the human merges. A crucible verdict other than SOUND blocks the merge listing.
  • Every flywheel ratified flip (A2/S/C decisions). Briefs propose paste-ready text.
  • liveRender — a live bounded render probe on the artist's Houdini. Never inferred from enthusiasm; only from the explicit flag.
  • Any dry_run default flip (A3 converter) and any registry rung promotion past L3 (P8).

Read the full file on GitHub · 54 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. 8d ago First seen · 54 lines · 140 tokens per session scan A 2750c4402448

Subscribe to this mod's changes

rsi-closure-orchestrator is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 808 once invoked, about $0.0007 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.