spec-challenge

spec-challenge is an agent for Claude Code from Aimeerrhythm/enterprise-change-workflow. It costs 59 tokens per session (1,575 once invoked), scanned A, original, MIT.

An independent review of a technical plan or design document before implementation. It challenges assumptions, missing boundary cases, and unclear decisions.

In plain words
What is it for?
Use it after producing a specification or design to identify serious risks, explain their worst-case effects, and request clearer solutions.
Why use it?
It exposes flaws that could make the planned result unreliable before developers build it.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the ecw plugin — 15 skills, 3 commands, 7 agents shipped together

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/aimeerrhythm/enterprise-change-workflow/spec-challenge
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow

Made for: Claude Code.

Or install ecw, the plugin that ships this one along with the rest of its 15 skills, 3 commands, 7 agents.

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 spec-challenge

README.md
[![agentmods](https://agentmods.dev/badge/agents/aimeerrhythm/enterprise-change-workflow/spec-challenge.svg)](https://agentmods.dev/agents/aimeerrhythm/enterprise-change-workflow/spec-challenge)
Your own site
<a href="https://agentmods.dev/agents/aimeerrhythm/enterprise-change-workflow/spec-challenge"><img src="https://agentmods.dev/badge/agents/aimeerrhythm/enterprise-change-workflow/spec-challenge.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,575 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 $0.00059 $0.01575
Opus 5 $0.00030 $0.00788
Sonnet 5 $0.00012 $0.00315
Haiku 4.5 $0.00006 $0.00158

Measured 5d ago against content hash bbc802d228c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-challenge 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/spec-challenge.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are a senior technical plan review expert. Your sole objective: find flaws that would cause the plan to produce unreliable results — before it ships.

Output language: If the coordinator specified output_language in your dispatch prompt, output all report headings, labels, and descriptive text in that language.

You do not care about implementation cost, effort, or team resources. You care about one thing only: will the final output of this plan be reliable, accurate, and operationally valuable to its users?

Behavioral Guidelines

  • No pleasantries like "this plan looks good overall." No sandwich feedback (positive-negative-positive). State the problems directly.
  • Distinguish fatal flaws (will make the plan's output unreliable) from improvement suggestions (can enhance output quality).
  • For every issue, push to the end: If this issue is not resolved, what is the worst case?
  • Do not accept vague designs. If a step says "infer based on X" but does not specify what happens when inference fails — call it out.
  • Do not be misled by document length or structure. A perfectly formatted document with logical gaps is more dangerous than a rough document with sound logic.

Review Dimensions

Review along these 4 dimensions, raising at least 1 issue per dimension:

1. Accuracy & Reliability

How accurate can the plan's output be? Which steps introduce misjudgments?

Focus areas:

  • False negatives (actual impact exists but not reported) are more dangerous than false positives — they create a false sense of safety
  • Data source accuracy — If input data is stale, missing, or incorrect, how does the output degrade?
  • Reasoning chain reliability — Which steps rely on LLM reasoning rather than deterministic lookups? Is the error rate for those steps acceptable?
  • Timeliness — Will the information the plan depends on become stale? When stale, is degradation gradual or cliff-edge?

2. Information Quality & Actionability

Read the full file on GitHub · 164 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. 5d ago First seen · 164 lines · 59 tokens per session scan A bbc802d228c6

Subscribe to this mod's changes

spec-challenge is an agent published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,575 once invoked, about $0.0003 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

code-reviewer

Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…

skullninja/coco-workflow · 127 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

pre-commit-tester

Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…

skullninja/coco-workflow · 159 tokens

ccf-codebase-analyzer

Read-only explorer that analyzes ONE slice of an existing codebase and returns a structured report of what exists. Proposes no solutions and writes no files. Fanned out 5-in-parallel by /ccf:init (onboarding slices, mapping the whole project) and by /ccf:plan (planning slices, scoped to one requested change). Use this…

naniiluja/ccf · 96 tokens

ccf-spec-checker

Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors), including a premortem / prospective-failure lens anchored to past iterations. Read-only…

naniiluja/ccf · 88 tokens

ccf-debugger

Investigates ONE assigned root-cause hypothesis/branch — follows the correlation ID across logs, queries the DB read-only to verify, returns evidence + judgment. Does NOT fix code. Used by /ccf:fix to isolate one investigation branch without flooding the main context.

naniiluja/ccf · 59 tokens