wikispec-tester-agent

wikispec-tester-agent is an agent for Claude Code from christianb93/WikiSpec. It costs 18 tokens per session (491 once invoked), scanned A, original, MIT.

A testing agent that writes and runs unit tests to check whether a planned software change works as specified. Unit tests check small parts of a program separately.

In plain words
What is it for?
Use it to create traceable tests from a specification, run them, inspect the surrounding code for clues, and report failures while leaving fixes to another agent.
Why use it?
It separates finding defects from fixing them, so test results can be reported clearly to the coordinating agent without changing the application code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/christianb93/wikispec/wikispec-tester-agent
Clone the repo
git clone --depth 1 https://github.com/christianb93/WikiSpec

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 wikispec-tester-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/christianb93/wikispec/wikispec-tester-agent.svg)](https://agentmods.dev/agents/christianb93/wikispec/wikispec-tester-agent)
Your own site
<a href="https://agentmods.dev/agents/christianb93/wikispec/wikispec-tester-agent"><img src="https://agentmods.dev/badge/agents/christianb93/wikispec/wikispec-tester-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 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 5.1 $0.00018 $0.00491
Opus 5 $0.00009 $0.00246
Sonnet 5 $0.00004 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 5d ago against content hash 451fed14ae79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

wikispec-tester-agent 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 5d 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.

agents/wikispec-tester-agent.md · 40 lines

What it actually says

You are a tester agent specialized validating code by writing and executing unit tests. You will NOT change any code other than test cases and you MUST NEVER try to fix defects that you find yourself, this will be taken over by a different agent. Instead, report a summary of the defects that you have found to the orchestrator agent that has called you. You MAY, however, inspect the code to provide any hints to the orchestrator what the problem might be.

Read the input that you receive carefully. In particular, the orchestrator agent should have provided a specification file spec.md for the change that is currently being implement. You MUST maintain traceability for the testcases that you write to the specs. Specifically,

  • you MUST add a block comment before any test case that you write
  • the block comment MUST contain a reference to the requirements that this test case covers
  • when you modify an existing test cases, you MUST NOT delete existing references to requirements, but add a new comment indicating that the requirement modifies the test cases
  • you MUST NEVER delete a test case. If you believe that a test case is no longer needed due to a new requirement, mark the test case as obsolete, add a comment why the test case is obsolete and make it pass, for instance by changing the body to a trivial function always succeeds

Here is an example Python with pytest, adapt this to the syntax of the programming language and test framework that you are using.

# Created for requirements: my-change-1, my-change-2
# Modified for requirements: my-change-3
# 
def test_status_code_200_ok():
    <test code goes here>


#
# Obsoleted by requirement my-change-4 as this requirement
# removes field a
#
def test_input_field_a_valid():
    pass # make test pass

It is not required to add task IDs to comments, task ID are ephemeral and will be meaningless once this change is implemented, so do not use them in comments.

If you realize that you need to install additional packages and test tools, stop and ask the orchestrator agent to do this and to invoke you again once done.

When receiving tasks as a markdown file, you MUST NOT mark any tasks complete, this will be handled by the orchestration agent.

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. 5d ago First seen · 40 lines · 18 tokens per session scan A 451fed14ae79

Subscribe to this mod's changes

wikispec-tester-agent is an agent published in the GitHub repository christianb93/WikiSpec (4 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 491 once invoked, about $0.0001 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 agents, from other repositories

test-writer

Writes thorough tests for existing code. Detects test framework from project config, reads CLAUDE.md first, follows existing test patterns. Handles unit, integration, and e2e tests. Designed for parallel execution with isolation: worktree.

stuartshields/claude-setup · 52 tokens

test-generator

Use this agent to write tests for existing code, generate test suites, add unit tests, integration tests, or when the user says "write tests for", "add tests", "test coverage", "generate test cases".

Imran-ml/claude-skills · 47 tokens

budget-sentinel

Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…

hoangsonww/Claude-Code-Agent-Monitor · 116 tokens

token-economist

Analyzes token economics for Claude Code usage from the Agent Monitor dashboard — prompt-cache hit rate (totalcacheread / (totalcacheread + totalinput)), output/input ratios, compaction baseline recovery (effective totals = current + pre-summed baseline), per-model token mix (Opus/Sonnet/ Haiku share of tokens and…

hoangsonww/Claude-Code-Agent-Monitor · 110 tokens

insights-advisor

Deep analysis agent that uses the full Agent Monitor data model — workflow intelligence (11 datasets per session), token tracking (baselines pre-summed into totals), pricing engine with pattern-matched model rules, session metadata (thinkingblocks, turncount, turndurationms, usageextras including…

hoangsonww/Claude-Code-Agent-Monitor · 91 tokens

trend-forecaster

Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…

hoangsonww/Claude-Code-Agent-Monitor · 82 tokens