Borrowing it
Nothing to install: this file belongs to sabbour/agentweaver. 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/sabbour/agentweaver/dev/.github/skills/agentweaver-api-harness/SKILL.mdgit clone --depth 1 https://github.com/sabbour/agentweaverWrote 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/skills/sabbour/agentweaver/agentweaver-api-harness)<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-api-harness"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-api-harness/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/skills/sabbour/agentweaver/agentweaver-api-harness"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-api-harness.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 | $0.00046 | $0.00482 |
| Opus 5.5 | $0.00018 | $0.00193 |
| Sonnet 5.5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
agentweaver-api-harness 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 1mo 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
API harness
Read scripts/api-harness/SKILL.md before
running the harness. It is the source of truth for its real CLI, flags, safety
controls, exit codes, evidence artifacts, and both supported modes:
- For a structured scenario or a re-test from a
reproManifest, invokenode scripts/api-harness/run-persona.mjswith a fresh scenario run. A manifest is provenance for a new comparable run—not an oldrunIdreplay. - For a free-text or exploratory persona investigation, dispatch a fresh
PersonaActorsub-agent with the persona brief. PersonaActor drives the live API itself and records its own transcript underscripts/api-harness/transcripts/. There is noagent-driverCLI.
Runs are unattended by default, and auto_approve_tools does not cover shell
commands: a run will emit shell.approval_required and stall forever unless
something approves it. Poll GET /api/runs/{id}/events and approve via
POST /api/runs/{id}/shell-approvals with {"command_hash": "<payload.commandHash>"},
or the run will look InProgress while making no progress at all.
Use the actual commands in that contract. Capture the output path, inspect the verdict/transcript JSON, and report the outcome with its evidence path and whether it is pass, fail, or inconclusive. Do not claim that a zero driver exit establishes subjective output quality.
Before running, check scripts/harness-shared/learnings.md (surface: api or all)
for already-known bugs, environment facts, and scenario-design notes so they aren't
rediscovered from source each run.
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.
- 1mo ago Changed · +7 lines d8cba9cb2982
- 1mo ago First seen · 31 lines · 46 tokens per session scan A 40611eb4f4af
agentweaver-api-harness is a skill published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 482 once invoked, about $0.0002 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 skills, from other repositories
csharp-dotnet
Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…
generate-microcks-openapi-samples
Use when creating OpenAPI mock examples for Microcks, setting up request/response routing with dispatchers, or mapping request fields to mock responses.
verify
Build, launch, and drive the AppointMe stack to verify a change end-to-end at its runtime surface.
schema-check
Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable verdict with native digest evidence.
cratis-application-slice-specifications
Specify the backend behavior of an event-sourced Cratis application slice — plain-call specs for pure decisions, plus CommandScenario, EventScenario, ReadModelScenario and ReactorScenario where the pipeline, validation, constraints or projections matter — including what to cover for each slice type and where the…
cratis-arc-command-operation
Declare immediate inline work as a Cratis Arc ICommandOperation returned by a model-bound command, with optional compensation and commit-aware recovery. Use when moving service writes out of Handle(), choosing operation return shapes, diagnosing recovery, or specifying execution and compensation through…