No. Anthropic Claude API returns a success response when it accepts the request. Provely proves all_succeeded and ended as separate promises.
| Fact | Value |
|---|---|
| Skill version | 0.1.0 |
| Publisher | Built and signed by Provely. |
| Certification | Provisional |
| Last conformance run | 2026-09-05T12:00:00Z: 26 of 26 cases passed, 0 critical false VERIFIED |
| Provider API versions | 2023-06-01 |
| Default provider API version | 2023-06-01 |
| Compiled | 2026-09-05 |
| Manifest hash | 1570330057d84a4b |
| Manifest hash check | the document hashes to the value the manifest states |
| Signature | valid, key provely-skill-2026-09, trusted by this build |
What does this page prove?
| Claim | Proven by | Evidence | Status |
|---|---|---|---|
| A batch that ended is not a batch whose requests succeeded. The level reads request_counts and refuses a batch that holds an error, an expiry, or a cancellation. | anthropic.message_batch.all_succeeded | E2 | proven |
| Every request of the batch succeeded, errored, was canceled, or expired. The level proves that the work stopped. It proves no result of any request. | anthropic.message_batch.ended | E2 | proven |
| An outcome outside Anthropic Claude API, such as a bank credit or a person who read a message | not proven | no E5 channel | not proven |
| The agent report that the action worked | never counts | E0 | not proven |
Which completion levels does the Anthropic Claude API skill expose?
Each level is one promise with one contract. An agent picks the level that matches the promise it makes. It cannot upgrade a level. Read the completion level definition.
| Level | Contract | Promise | Evidence | Certification |
|---|---|---|---|---|
all_succeeded | anthropic.message_batch.all_succeeded v1.0.0 | A batch that ended is not a batch whose requests succeeded. The level reads request_counts and refuses a batch that holds an error, an expiry, or a cancellation. | E2 | Provisional |
ended | anthropic.message_batch.ended v1.0.0 | Every request of the batch succeeded, errored, was canceled, or expired. The level proves that the work stopped. It proves no result of any request. | E2 | Provisional |
Which ways can a Anthropic Claude API action look done and not be?
| Contract | Case | Verdict |
|---|---|---|
| anthropic.message_batch.all_succeeded | duplicate side effect | CONTRADICTED |
| anthropic.message_batch.all_succeeded | pre existing state | CONTRADICTED |
| anthropic.message_batch.all_succeeded | wrong subject | CONTRADICTED |
| anthropic.message_batch.ended | duplicate side effect | CONTRADICTED |
| anthropic.message_batch.ended | pre existing state | CONTRADICTED |
| anthropic.message_batch.ended | wrong subject | CONTRADICTED |
What did the last conformance run show?
The last conformance run on 2026-09-05T12:00:00Z passed 26 of 26 cases with 0 critical false VERIFIED. One critical false VERIFIED rejects a skill.
| Contract | Certification |
|---|---|
anthropic.message_batch.all_succeeded | Provisional |
anthropic.message_batch.ended | Provisional |
The weakest contract is anthropic.message_batch.all_succeeded. It reaches Provisional. The package level is Provisional, because a package level never rises above its weakest contract. Read the level of the contract you use.
| Case class | Passed | Total |
|---|---|---|
| duplicate side effect | 2 | 2 |
| error after execution | 2 | 2 |
| error before execution | 2 | 2 |
| evidence unavailable | 2 | 2 |
| pre existing state | 2 | 2 |
| stale readback | 2 | 2 |
| still transitional | 2 | 2 |
| terminal failure | 2 | 2 |
| terminal success | 3 | 3 |
| timeout after commit | 2 | 2 |
| version mismatch | 2 | 2 |
| wrong subject | 2 | 2 |
| wrong terminal state | 1 | 1 |
The conformance artifact digest is eae45ca3048c69c3. The harness signs the run, so a reader can check that these numbers come from that run.
What remains uncertain?
The level is Provisional because of it. Provely does not guess a rule that a source does not state.
Where do these facts come from?
Every claim above cites a source assertion in the skill provenance. The compiler records the source, its hash, and the retrieval date. A page never states a provider rule without one.
| Source | Kind | Retrieved | Excerpt |
|---|---|---|---|
| anthropic.docs.batch_object | docs | 2026-09-09 | authored |
| anthropic.docs.batches | docs | 2026-09-09 | authored |
| anthropic.docs.files | docs | 2026-09-09 | authored |
| anthropic.docs.versions | docs | 2026-09-09 | authored |
| anthropic.openapi | openapi | 2026-09-09 | authored |
How do I verify a Anthropic Claude API action?
Verify a Anthropic Claude API action with Provely
- Begin the operation.Call
beginwith the contractanthropic.message_batch.all_succeededand the input. Keep the operation id. - Make the Anthropic Claude API call you make today.Send the request with the correlation metadata that
beginreturned. - Submit the acknowledgement.Call
action_resultwith the Anthropic Claude API response. This is evidence level E1. It is not completion. - Verify.Call
verify. The runtime reads the evidence that the contract names, from Anthropic Claude API and not from the agent, and evaluates the contract. - Report the verdict exactly as returned.VERIFIED comes with a signed receipt. PENDING comes with the operation id. CONTRADICTED and UNVERIFIABLE are not success.
Questions developers ask
Does the all_succeeded level prove the ended level?
No. A batch that ended is not a batch whose requests succeeded. The level reads request_counts and refuses a batch that holds an error, an expiry, or a cancellation. Every request of the batch succeeded, errored, was canceled, or expired. The level proves that the work stopped. It proves no result of any request. Use anthropic.message_batch.ended to prove ended.
What does the agent say while the Anthropic Claude API action is still in progress?
It says: "The action is accepted but not yet verified. Operation: <id>." The verdict is PENDING. The runtime observes again on the contract timing policy.
Which Anthropic Claude API API versions does the skill support?
2023-06-01. An operation on another version returns UNVERIFIABLE with the reason version_unsupported. The runtime never guesses.
Does Provely need write access to Anthropic Claude API?
No. The agent keeps its write key. The verifier reads with a separate read-only credential where Anthropic Claude API permits it, and it never shares that credential with the agent.