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.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/agents/rsi-closure-orchestrator.mdgit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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.
[](https://agentmods.dev/agents/josephoibrahim/synapse/rsi-closure-orchestrator)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/rsi-closure-orchestrator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/rsi-closure-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00140 | $0.00808 |
| Opus 5.5 | $0.00056 | $0.00323 |
| Sonnet 5.5 | $0.00028 | $0.00162 |
| Haiku 4.5 | $0.00014 | $0.00081 |
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 2mo 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.
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:
- SIGNAL — fix the three loops that cannot observe their own failure (A1, F, E).
- 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.
- 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)
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.python harness/progress.py --fast— what else is running; never double-dispatch into a tree with live worktree forges (Article V collision history).git status --porcelain --untracked-files=no— a dirty tree blocks SIGNAL dispatch.- Read
harness/rsi/REGISTRY.jsonrungs — 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
ratifiedflip (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_rundefault flip (A3 converter) and any registry rung promotion past L3 (P8).
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.
- 2mo ago First seen · 54 lines · 140 tokens per session scan A 2750c4402448
rsi-closure-orchestrator is an agent published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 808 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
wizard
Deep review, hard debugging, and "which approach" calls. Read-only. Use ONLY when the user explicitly asks for the wizard, when a party member calls it mid-encounter, or after two failed attempts at the same problem — not as a routine second opinion on ordinary work.