agentweaver: Skill for Claude Code

.github/skills/agentweaver-harness/SKILL.md

agentweaver-harness is a skill for Claude Code from sabbour/agentweaver. It costs 48 tokens per session (327 once invoked), scanned A, original, MIT.

A test runner for checking an Agentweaver system through its API, user interface, and MCP connections in one pass.

In plain words
What is it for?
Use it for full validation, regression checks, or exploratory testing. For a focused investigation, use the runner for just one surface.
Why use it?
It collects results from several surfaces together, making cross-surface failures and regressions easier to spot.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is sabbour/agentweaver's own configuration. It tells Claude Code how to work on agentweaver itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentweaver configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(node scripts/combined-harness/launch.mjs:*).

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/sabbour/agentweaver/dev/.github/skills/agentweaver-harness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

Made for: Claude Code.

Wrote 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.

agentmods badge for agentweaver-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-harness.svg)](https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-harness)
Your own site
<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-harness"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00327
Opus 5 $0.00024 $0.00163
Sonnet 5 $0.00010 $0.00065
Haiku 4.5 $0.00005 $0.00033

Measured 6d ago against content hash e22e266be204, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agentweaver-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 6d 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.

.github/skills/agentweaver-harness/SKILL.md · 28 lines

What it actually says

Combined Agentweaver harness

Use this skill for a full cross-surface sweep. It starts the selected API, UI, and MCP harness commands as independent parallel processes, assigns one batchId, and then runs the shared meta-aggregator. Findings correlate only on (batchId, scenarioId), never runId.

Read scripts/combined-harness/README.md before invoking it. Supply each surface command as a JSON argv array and use {batchId}, {scenarioId}, and {verdictDir} placeholders so every harness writes its canonical verdict into the isolated verdict directory.

Use agentweaver-api-harness, agentweaver-ui-harness, or agentweaver-mcp-harness instead for targeted investigation of one surface. This launcher does not recreate any surface driver or judging logic.

Before running, check scripts/harness-shared/learnings.md (surface: all, plus each selected surface) for already-known bugs, environment facts, and scenario-design notes so they aren't rediscovered from source each run.

Changes

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.

  1. 6d ago First seen · 28 lines · 48 tokens per session scan A e22e266be204

Subscribe to this mod's changes

agentweaver-harness is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 327 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

codew-release-qa-sweep

Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.

Hmbown/CodeWhale · 31 tokens

mcp-app-verification

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

a5c-ai/babysitter · 48 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

migrate-xunit-to-xunit-v3

Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…

managedcode/dotnet-skills · 149 tokens

spec-execution

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

a5c-ai/babysitter · 30 tokens

tdd-enforcement

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

a5c-ai/babysitter · 33 tokens