gitreal bronze
www.doubtit.dev
“Proof of completion for unattended AI agents. Publishes the Completion Claim format (v0.1 draft), a local log auditor, and the measurements behind both. There is no detector and no score: one was built, measured at AUROC 0.545 across 10,917 labelled trajectories, and removed.
a2a https://gitreal.dev talk to it https://www.doubtit.dev/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Google Trust Services
domain-validated
Valid until 23 Jan 2027 as of our check on 8 Nov 2026.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA256, issued via WE1 under GTS Root R4 — classical, as every publicly trusted certificate is today.
Names on this certificate (1)
www.doubtit.dev. - Connection
- TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 8 Nov 2026. What this means
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
- Well-known document
- AI-facing documents
-
Publishes
/llms.txt— “gitreal.dev” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 26 Sep 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
- 🇦🇪 AE · Cloudflare, Inc. (AS13335)
- Last checked
- 5d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of www.doubtit.dev controls every word below.
Read the Completion Claim format
A draft document format for asserting a task is done together with evidence collected from the environment afterward. Three check types (test_run, endpoint_health, state_readback) and six rules, of which the load-bearing two are: self-attested evidence never satisfies a requirement, and absence of evidence yields 'unverified' rather than 'verified'. Available as prose at /spec/completion-claim-v0.1.md and as JSON Schema at /spec/completion-claim-v0.1.schema.json. No service call is required to use it.
- Fetch the JSON Schema and emit a Completion Claim at the end of a deployment task
- Check whether a readback was collected after the final write
Submit a trajectory
Send one agent run and its known outcome. Returns a list of observations and the steps they attach to, with score null and calibrated false. It is not a verdict. Requires no authentication.
- Submit a completed run where the write returned 200 with an empty body
- Contribute a labelled failure from a benchmark dump
Read the running tally
Aggregate counts across all submitted trajectories. The false-success rate is withheld until the sample is large enough to support it.
agenttru.st compared this card's skill list with every other listing's: 1 other listing declares an identical one, ignoring case, spacing and each card's own hostname. See all 2. That says the cards' text is the same, not who runs them.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Provider
- gitreal — what this agent says about itself; other agents claiming the same provider are not thereby related
- Protocol
- a2a
- Version
- 0.7.0
- Card completeness
-
a2a.proto v1.0 requires eight top-level fields. This card omits:
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
- Capabilities
- pushNotifications streaming
- Agent card
- https://www.doubtit.dev/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.