Robin Saige we check the tools AI agents call

arifOS — Constitutional AI Kernel

io.github.ariffazil/arifos

Constitutional AI kernel with 13 MCP tools, 888_JUDGE verdict pipeline, and VAULT999 ledger.

— the operator's own registry description reported

Publisher io.github.ariffazil · first seen 2026-08-12 · endpoint https://arifos.arif-fazil.com/mcp

allow
verdict
mid-slow-shared
cluster
ok_tools
answers
8
tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V0 take its word ◐
allow — because answers ●, 8 tools legible (band C) ●, no confirmed drift in 6 probes ●; not yet checked: truth (0 runs)

Cluster mid-slow-shared · distinctiveness 0.66 (unusual). Every figure is a percentile or class within the 15,472-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency763 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools8
vs populationmid
capabilities7
harnessC
Did it hold when checked? Q3–Q4 · derived
identityshared
servers on its host1
servers on its domain2
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_692b5d334c98df5be5a98f13 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Q1Does it answer?alive & usable — 6 probes ●evidence ↓
Q2What is it?retrieval-public ● evidence ↓
Q3Can it be checked?V0 take its word ◐evidence ↓
Q4Did it hold?harness C · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?mid-slow-shared · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (6 shown, 2026-08-12 → 2026-09-06). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (2 events)
datetypewhat changed
2026-08-23outcomeok_tools (was http_error)
2026-08-12outcomefirst probe: http_error

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
action3changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public3serves public factstruth-checkable against a public source — the V-ladder applies in full
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)
unclassified1not classifiable from its textTier-1 only until its tools describe themselves

Tools last seen observed

arif_forge arif_init arif_judge arif_memory arif_observe arif_route arif_seal arif_think

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band C — callable but under-described.

legibility checktools passingok
name is clear & specific8/8
has a description8/8
description is substantive8/8
parameters are typed0/80/8
parameters are described0/80/8

8 of 8 tools graded · 8 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18
protocol version
session model
kanon-2026.09.04+7a49cce
server version ARIFOS MCP

Capabilities: experimental extensions logging prompts resources tasks tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-06; changes appear here after human review.

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-09-06T06:15:44Zok_tools2007632025-06-18
2026-08-30T06:15:20Zok_tools20011012025-06-18
2026-08-23T06:13:09Zok_tools2007982025-06-18
2026-08-16T06:12:56Zhttp_error400853
2026-08-14T19:59:23Zhttp_error400760
2026-08-12T05:34:35Zhttp_error400803

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.ariffazil/arifos.svg)](https://robinsaige.com/s/io.github.ariffazil/arifos)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →