reason-about-dependencies

reason-about-dependencies is a skill for Claude Code, Codex from tetracoralla/deterministic-dependency-engine. It costs 67 tokens per session (268 once invoked), scanned A, original, Apache-2.0.

A skill for answering dependency questions from an explicitly listed graph, where a graph is a set of connected items and their relationships. It can identify prerequisites, ready work, blockers, execution order, affected items, and explanation paths.

In plain words
What is it for?
Use it to resolve work order, find blockers, assess the impact of changes, select a relevant part of a dependency graph, explain paths, or validate cycles and ordering.
Why use it?
It avoids guessing relationships that were not provided and keeps dependency answers consistent when the graph is valid.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to resolve work order, find blockers, assess the impact of changes, select a relevant part of a dependency graph, explain paths, or validate cycles and ordering.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tetracoralla/deterministic-dependency-engine/reason-about-dependencies
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.

Any agent
npx skills add tetracoralla/deterministic-dependency-engine --skill reason-about-dependencies
Clone the repo
git clone --depth 1 https://github.com/tetracoralla/deterministic-dependency-engine

Made for: Claude Code, Codex.

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 reason-about-dependencies

README.md
[![agentmods](https://agentmods.dev/badge/skills/tetracoralla/deterministic-dependency-engine/reason-about-dependencies.svg)](https://agentmods.dev/skills/tetracoralla/deterministic-dependency-engine/reason-about-dependencies)
Your own site
<a href="https://agentmods.dev/skills/tetracoralla/deterministic-dependency-engine/reason-about-dependencies"><img src="https://agentmods.dev/badge/skills/tetracoralla/deterministic-dependency-engine/reason-about-dependencies.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00067 $0.00268
Opus 5 $0.00034 $0.00134
Sonnet 5 $0.00013 $0.00054
Haiku 4.5 $0.00007 $0.00027

Measured 7d ago against content hash 7af0ddab6ab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reason-about-dependencies 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 7d 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.

skills/reason-about-dependencies/SKILL.md · 22 lines

What it actually says

Reason about declared dependencies with Deterministic Dependency Engine

Call the matching direct tool once. Supply the graph with explicit dependent and prerequisite fields; never translate it to from / to.

  • Use dependency_resolve for what remains, what is ready, and execution order.
  • Use dependency_impact for downstream effects of changed nodes.
  • Use dependency_explain for blocker paths or one impact path.
  • Use dependency_slice when only the minimal relevant graph is needed.
  • Use graph_validate when legality, cycles, or ordering is the question.

Treat satisfied and changed as query-local facts, not graph properties. A cycle or invalid graph is a result to repair, not permission to guess an order. Present the actionable structured result compactly. A calculation receipt only identifies the computation; never describe it as proof that the declared relations are true.

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. 7d ago First seen · 22 lines · 67 tokens per session scan A 7af0ddab6ab9

Subscribe to this mod's changes

reason-about-dependencies is a skill published in the GitHub repository tetracoralla/deterministic-dependency-engine (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 67 tokens to every session and 268 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 skills, from other repositories