Check that a sub-agent delegation states objective, acceptance criteria, budget, evidence and stop conditions
Checks the brief an agent is about to hand to another agent: the required parts are present and non-empty (objective, acceptance criteria, a budget with at least one positive numeric bound, required evidence, stop conditions; output format if required), nothing is duplicated, and acceptance criteria are not made only of vague wording (a small labelled word list: good, appropriate, if possible ...). fail = a required part is missing or a budget bound is not positive; unknown = only vague-wording hints or repeated entries; pass = all present and distinct. Does not judge whether the task is sensible or the criteria sufficient.
What you get
Delegations without a budget, evidence or stop condition are the ones that run away or come back unverifiable.
Call it
Send the JSON body below to https://agents.writerslogic.com/api/v1/delegation-contract-check. An unpaid request answers 402 with the price and how to pay; a request that fails with a 5xx status is not charged.
curl -i -X POST https://agents.writerslogic.com/api/v1/delegation-contract-check \
-H 'content-type: application/json' \
-d '{"objective":"List every endpoint in src/routes that lacks auth middleware.","acceptanceCriteria":["Output is a JSON array of {file,line,route}","Every file under src/routes was read"],"budget":{"maxToolCalls":40,"maxSeconds":300},"evidenceRequired":["paths of files read"],"stopConditions":["all files read","budget spent: report partial results"]}'
Input
| Field | Type | Required | Description |
|---|---|---|---|
objective | string; length 0..2000 | no | |
acceptanceCriteria | array<string; length 0..2000>; max 30 items | no | |
budget | object | no | |
evidenceRequired | array<string; length 0..2000>; max 30 items | no | What the delegate must return as proof (links, test output, file paths). |
stopConditions | array<string; length 0..2000>; max 30 items | no | When the delegate must stop and report (done, blocked, budget spent). |
outputFormat | string; length 0..2000 | no | |
require | array<string; one of "objective", "acceptanceCriteria", "budget", "evidenceRequired", "stopConditions", "outputFormat">; max 6 items | no | Parts that must be present. Default: objective, acceptanceCriteria, budget, evidenceRequired, stopConditions. |
Example request body
{
"objective": "List every endpoint in src/routes that lacks auth middleware.",
"acceptanceCriteria": [
"Output is a JSON array of {file,line,route}",
"Every file under src/routes was read"
],
"budget": {
"maxToolCalls": 40,
"maxSeconds": 300
},
"evidenceRequired": [
"paths of files read"
],
"stopConditions": [
"all files read",
"budget spent: report partial results"
]
}
Result
The response is { "data": ..., "_provenance": ... }. data carries these fields; _provenance is a signed W3C Verifiable Credential with a C2PA-style manifest, checked free at POST /api/v1/verify-provenance.
| Field | Type | Required | Description |
|---|---|---|---|
status | string; one of "pass", "fail", "unknown", "unsupported" | no | pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass. |
missing | array<string> | no | |
vagueCriteria | array<integer> | no | Indexes of acceptance criteria containing vague wording (heuristic word list). |
budgetBounds | array<string> | no | Budget fields that are set to a positive value. |
witnesses | array<object> | no | |
versions | object | no | Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile). |
limits | array<string> | no | |
deterministic | boolean | no | Always true: pure code, no model. |
Pay and connect
Available through: x402 (USDC on Base), MCP. MCP clients reach it through the execution-safety-kit package.
Machine-readable
- This agent as JSON (schemas, example, OpenAPI operation)
- Free signed sample response
- OpenAPI 3.1 · Catalog · Index of every agent