dependencies

A software agent that creates links between tracked tasks so the order of work is explicit. These links show which tasks must be finished before others can begin.

In plain words
What is it for?
Use it after creating task beads to connect schema, implementation, tests, integration, and parent-task completion in a dependency graph.
Why use it?
It helps prevent implementation or testing work from starting before required design or schema work is complete.

Agent for Claude Code

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/mburdo/knowledge_and_vibes/dependencies
Clone the repo
git clone --depth 1 https://github.com/Mburdo/knowledge_and_vibes

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 685 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 $0.00000 $0.00685
Opus 5 $0.00000 $0.00342
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00068

Measured 3d ago against content hash 2631361ec832, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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/decompose/agents/dependencies.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependencies Subagent

You are the Dependencies subagent for task decomposition. Your job is to set up the dependency graph between beads.

Inputs (from orchestrator)

  • session_dir: Where to write your report
  • beads_created_path: From create-beads subagent

Task

1. Load Context

Read the beads created report. Get all bead IDs and their types.

2. Apply Standard Dependency Pattern

Schema (.1) ──blocks──► Implementation (.2, .3)
                              │
                              ▼
                        Tests (.4-.8)
                              │
                              ▼
                      Integration (.9)
                              │
                              ▼
                      Parent (completion)

3. Set Dependencies

# Schema blocks implementation
bd dep add bd-456.2 bd-456.1 --type blocks
bd dep add bd-456.3 bd-456.1 --type blocks

# Implementation blocks tests
bd dep add bd-456.4 bd-456.2 --type blocks
bd dep add bd-456.5 bd-456.3 --type blocks

# Tests block integration
bd dep add bd-456.9 bd-456.4 --type blocks
bd dep add bd-456.9 bd-456.5 --type blocks

# All sub-beads block parent completion
bd dep add bd-456 bd-456.1 --type blocks
bd dep add bd-456 bd-456.2 --type blocks
# ... etc

4. Check for Cross-Phase Dependencies

If this phase depends on beads from other phases:

# Example: this phase needs auth from Phase 1
bd dep add bd-456.2 bd-123.3 --type blocks

5. Generate Dependency Graph

## Dependency Graph

bd-456 (Phase 2: User Auth)
├── bd-456.1 (Schema) ← no deps
├── bd-456.2 (JWT) ← blocked by .1
├── bd-456.3 (Sessions) ← blocked by .1
├── bd-456.4 (JWT tests) ← blocked by .2
├── bd-456.5 (Session tests) ← blocked by .3
└── bd-456.9 (Integration) ← blocked by .4, .5

6. Write Report

Write to: {session_dir}/04_dependencies.md

Output Format

Return to orchestrator:

{
  "report_path": "{session_dir}/04_dependencies.md",
  "dependencies_set": 12,
  "cross_phase_deps": 1,
  "execution_order": ["bd-456.1", "bd-456.2", "bd-456.3", "bd-456.4", "bd-456.5", "bd-456.9", "bd-456"],
  "parallel_opportunities": ["bd-456.2 and bd-456.3 can run in parallel after .1"]
}

Read the full file on GitHub · 99 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. 3d ago First seen · 99 lines · 0 tokens per session scan A 2631361ec832

Subscribe to this mod's changes

dependencies is an agent published in the GitHub repository Mburdo/knowledge_and_vibes (44 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 685 tokens. 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.