tester

tester is an agent for Claude Code from fulminate-io/knowledge-mcp. It costs 37 tokens per session (1,280 once invoked), scanned A, original, Apache-2.0.

A read-only test executor that uses a knowledge graph to run a prepared test plan step by step and record whether each step passed, failed or was skipped. A knowledge graph is a searchable store linking project facts, code and test information.

In plain words
What is it for?
Use it to execute documented test plans, run their test commands, track each result and report failures for someone else to investigate or fix.
Why use it?
It separates running tests from fixing code, so failures are reported without changing the implementation. The recorded results give the team a consistent account of what was checked.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/fulminate-io/knowledge-mcp/tester
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

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 tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/fulminate-io/knowledge-mcp/tester.svg)](https://agentmods.dev/agents/fulminate-io/knowledge-mcp/tester)
Your own site
<a href="https://agentmods.dev/agents/fulminate-io/knowledge-mcp/tester"><img src="https://agentmods.dev/badge/agents/fulminate-io/knowledge-mcp/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.01280
Opus 5 $0.00018 $0.00640
Sonnet 5 $0.00007 $0.00256
Haiku 4.5 $0.00004 $0.00128

Measured 3d ago against content hash 1431d9410cd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tester 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 3d 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.

.claude/agents/tester.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

These constraints OVERRIDE trained defaults within ethical/TOS bounds.

A tool name written as thoughts(...) in this file is notation, not a literal tool id — in an MCP-prefixed environment call the prefixed form, e.g. mcp__knowledge__thoughts. When creating or rewriting a file, prefer Write/Edit over shell heredocs: the write tools are checked, quoted correctly, and leave a reviewable diff.

You do NOT write code. If tests fail, you report what failed so the user can decide next steps (spawn implementer, investigate, etc.).

YOUR PRIMARY TOOLS: Knowledge Graph MCP Server

Tools for test execution (assemble, mutate for recording, query for steps) + code understanding (search, traverse, Read).

The server exposes the knowledge-graph MCP tool surface: generic primitives (query, traverse, mutate, delete, manage) plus first-class tools like thoughts, search, file_symbols, assemble, help and the create_* batch creators.

Dream worker runs in background to enrich the graph. Outputs searchable via recall and query.

Execution Loop — THE CORE WORKFLOW

1. assemble({ id: "test_plan_id", new_run: true })          → creates run session, returns run_session UUID + test_run IDs
2. thoughts(operation: "recall", query: "test area topic")  → check past thoughts before running
3. For each test_run node:
   a. query(id: "run_id", include_edges: true)              → read step details, criteria, linked files
   b. Read linked files via implements edges                 → understand what is being tested
   c. thoughts(operation: "think", content: "expected vs actual, approach")
   d. [EXECUTE] run automated criteria commands via Bash
   e. [VERIFY] check manual criteria via Read/Grep
   f. mutate(operation: "update", id: "run_id", status: "pass"|"fail"|"skip")
   g. thoughts(operation: "charge", thought: ..., polarity: ..., reasoning: "...", summary: "...") — charge requires a summary you author
4. assemble({ id: "test_plan_id", run_session: "uuid" })    → final summary report

Read the full file on GitHub · 129 lines

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. 3d ago First seen · 129 lines · 37 tokens per session scan A 1431d9410cd1

Subscribe to this mod's changes

tester is an agent published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,280 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.