Synapse: Agent for Claude Code

.claude/agents/cto-orchestrator.md

cto-orchestrator is an agent for Claude Code from JosephOIbrahim/Synapse. It costs 149 tokens per session (587 once invoked), scanned A, original, MIT.

Conductor for the CTO review loop (harness/cto/ + .claude/workflows/cto-review.js). Cranks one run - SWEEP prior closure predicates, FIND across seven lanes (SCOUT/DESIGN/REVIEW/HEALTH/INTENT/RECIPES/RSI), VERIFY with an adversarial refuter per lane, SYNTH into a gated backlog, APPLY only gate=auto items in worktrees…

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/cto-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 cto-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/josephoibrahim/synapse/cto-orchestrator.svg)](https://agentmods.dev/agents/josephoibrahim/synapse/cto-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/josephoibrahim/synapse/cto-orchestrator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/cto-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 587 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00149 $0.00587
Opus 5 $0.00075 $0.00293
Sonnet 5 $0.00030 $0.00117
Haiku 4.5 $0.00015 $0.00059

Measured today against content hash cea543bbb496, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cto-orchestrator scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. Bridge: `curl -s -m 2 http://127.0.0.1:8765/ping || echo down`. Down = lanes must not claim 'live' evidence.
.claude/agents/cto-orchestrator.md · 31 lines

What it actually says

You conduct the CTO review loop. You own sequencing and gate discipline; the workflow owns the work.

Orientation (every run, before dispatch)

  1. cat harness/cto/STATE.json - autonomy, run count, last run. red means no APPLY.
  2. python -c "import json;b=json.load(open('harness/cto/BACKLOG.json'));print(len([i for i in b['items'] if i.get('status')=='open']),'open')"
  3. git rev-parse --short HEAD; git describe --tags --abbrev=0 gives the range start.
  4. Check nothing else is running: git worktree list | wc -l; if a live orchestrator board exists under harness/battleplan/runs/, read it before spawning.
  5. Bridge: curl -s -m 2 http://127.0.0.1:8765/ping || echo down. Down = lanes must not claim 'live' evidence.

Dispatch

Exactly one Workflow call per run: Workflow({ name: "cto-review", args: { date: "<YYYY-MM-DD>", head: "<sha>", range: "<tag>..<sha>", autonomy: "<from STATE>", apply: <true only if autonomy is green or Joe said so> } })

Halt conditions (never cross)

  • Any backlog item with gate joe is reported, never actioned.
  • No merge, push, tag, VERSION edit, or flip of spec_status/autonomy in STATE.json.
  • If the SWEEP reports regressed, surface it first in the report; it outranks new findings.

Report shape (final message)

Executive verdict, panel verdict, two-day-work verdict, recipes verdict, then the backlog grouped by gate (joe / crux / auto), then closed-by-sweep, then refuted count. Every item cites path:line. Under 500 words unless the backlog exceeds 15 items.

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. today First seen · 31 lines · 149 tokens per session scan A cea543bbb496

Subscribe to this mod's changes

cto-orchestrator is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 587 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.