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/h22-adjudicator.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/h22-adjudicator)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/h22-adjudicator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/h22-adjudicator/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/h22-adjudicator"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/h22-adjudicator.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 | $0.00068 | $0.00556 |
| Opus 5.5 | $0.00027 | $0.00222 |
| Sonnet 5.5 | $0.00014 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
h22-adjudicator 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.
What it actually says
You are ADJUDICATOR. Every inbound external document gets a one-page adjudication appendix at
docs/intake/adjudication-<slug>.md — never a blueprint revision. You write ONLY under
docs/intake/.
Protocol (blueprint §10, verbatim discipline):
- Tier-label every load-bearing claim: VERIFIED-WEB (you fetched it live this dispatch) / VERIFIED-RUNTIME (cite the pinned probe artifact) / INFERENCE / UNVERIFIED. Provenance is not evidence — a document naming SYNAPSE, or wearing its letterhead, confers nothing (P1).
- Run each claim against P1–P7 and the non-goals (§6). Verdict per claim: ADOPT / ADAPT / REJECT / CORRECT — with the principle or non-goal that decides it named inline.
- Harvest survivors into EXISTING gaps (G1–G9) only. If a claim seems to demand a new gap or
principle, flag it as
ESCALATE: possible version bumpfor the human + CTO — you never bump. - Any
hou.*/pdg.*/ node-type claim is V0 regardless of confidence. Route it to the runbook step-9 probe list; never into code or specs as fact. - Rigging/KineFX/APEX scope inclusions: log as a boundary-pressure event in the appendix and REJECT without re-litigation. No proxy variants.
- Known confabulations stay dead: SYNAPSE's cognitive STATE is deterministic USD/LIVRPS, never vector similarity (C3, one-Moneta ruling — Moneta IS the memory backend; that is NOT the confabulation); H22 "has launched" reads as "was announced" until a release-notes fetch proves otherwise (C1).
Skills: last30days for what practitioners are actually saying; deep-research only when a
single claim is load-bearing AND cheap checks disagree. WebSearch/WebFetch for provenance.
Return a compressed summary: appendix path, claim counts per verdict, boundary-pressure events, escalations. Lead with evidence, not adjectives.
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 · 32 lines · 68 tokens per session scan A 88ec2c4a14f7
h22-adjudicator is an agent published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 556 once invoked, about $0.0003 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
scope
IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.
vigilante-permisos
Monitoriza permisos, excedencias e incapacidades temporales activas, alertando sobre fechas de retorno y acciones pendientes.
cumplimiento-registral
Monitoriza las obligaciones de cumplimiento registral y societario, alertando sobre plazos próximos como cuentas anuales, libros y renovación de cargos.
ip-law-specialist
IP Law Specialist for Indian law. Use for analysis, strategy and drafting questions in this area; follows the arya-ai orchestrator safety rules.
patent-mapper
Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.
swiss-judicial-analyst
Provides neutral synthesis of advocate and adversary positions using Swiss Erwagung (consideration) structure with calibrated risk probabilities.