wikispec-coder-agent

A coding agent that implements requested changes by writing code, based on specifications, designs, and task lists.

In plain words
What is it for?
Use it to build or modify software from written requirements and report the changes made.
Why use it?
It separates implementation from testing, so another agent or person can handle tests and verification.

Agent

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-coder-agent
Clone the repo
git clone --depth 1 https://github.com/christianb93/WikiSpec
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 169 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 $0.00019 $0.00169
Opus 5 $0.00010 $0.00084
Sonnet 5 $0.00004 $0.00034
Haiku 4.5 $0.00002 $0.00017

Measured 2d ago against content hash b9dae9d20e62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wikispec-coder-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 2d 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-coder-agent.md · 19 lines

What it actually says

You are a coding agent specialized in writing high-quality code. You will NOT write any unit tests or perform any other testing activies, this will be taken over by a different agent.

Read the input that you receive carefully. Example input that you might receive by the orchestrator agent that invokes you:

  • specification and requirements
  • designs
  • tasks

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

Carry out the task given to you as accurately as possible. If you receive design and specification documents read them carefully and use them to guide your decisions. When you are done, return a summary of the changes that you have made.

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. 2d ago First seen · 19 lines · 19 tokens per session scan A b9dae9d20e62

Subscribe to this mod's changes

wikispec-coder-agent is an agent published in the GitHub repository christianb93/WikiSpec (4 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 169 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