specX

A guide for reading task specifications before implementing assigned work in xdel or xflow.

In plain words
What is it for?
Use it to understand a dispatched task, follow relevant project constraints, stay within scope, perform a self-review, and report completed checks.
Why use it?
It keeps an agent focused on its assigned files and acceptance criteria, and prevents it from guessing when documents conflict.

Skill for Claude CodeCodex

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 skills/treex-x/workflowx/specx
Any agent
npx skills add TreeX-X/WorkFlowX --skill specx
Clone the repo
git clone --depth 1 https://github.com/TreeX-X/WorkFlowX

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 210 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 $0.00018 $0.00210
Opus 5 $0.00009 $0.00105
Sonnet 5 $0.00004 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 2d ago against content hash 25320903bd56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specX 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.

.claude/skills/specX/SKILL.md · 29 lines

What it actually says

specX

Use only when coderX is dispatched by xdel or xflow with a Hybrid Tree task.

Before Editing

  • Read the dispatch task first.
  • Read the assigned Child acceptance criteria and file scope.
  • Read only the Parent sections required for ownership, dependencies, or global constraints.
  • Treat the dispatch interpretation and Child acceptance criteria as authoritative. Stop on contradictions instead of guessing.

During Implementation

  • Follow engineeringX for implementation principles and self-review.
  • Stay within the assigned Child scope. Report required shared-file or scope changes to the Main Agent.
  • Do not write to Parent or Child documents.
  • Expand context only when a named dependency or API contract requires it.

Completion

  • Perform the engineeringX self-review.
  • Run relevant checks when available and report what was actually run.
  • Return the mode-specific implementation summary or Bus Payload requested by the dispatch contract.
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 · 29 lines · 18 tokens per session scan A 25320903bd56

Subscribe to this mod's changes

specX is a skill published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 210 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 2026-08-30.