raci

raci is a command for Claude Code from Aznatkoiny/zAI-Skills. It costs 8 tokens per session (740 once invoked), scanned A, original, MIT.

A command that creates a RACI matrix, a table showing who does the work, makes the final decision, gives advice, or receives updates for each activity.

In plain words
What is it for?
Use it to assign roles for an initiative, clarify responsibilities across stakeholders, and check that each activity has exactly one accountable decision-maker.
Why use it?
It removes uncertainty about ownership and helps prevent decisions from having no owner or too many final decision-makers.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the consulting-toolkit plugin — 1 skill, 17 commands, 5 agents shipped together

Good fit Use it to assign roles for an initiative, clarify responsibilities across stakeholders, and check that each activity has exactly one accountable decision-maker.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/aznatkoiny/zai-skills/raci
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.

Clone the repo
git clone --depth 1 https://github.com/Aznatkoiny/zAI-Skills

Made for: Claude Code.

Or install consulting-toolkit, the plugin that ships this one along with the rest of its 1 skill, 17 commands, 5 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 raci

README.md
[![agentmods](https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/raci.svg)](https://agentmods.dev/commands/aznatkoiny/zai-skills/raci)
Your own site
<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/raci"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/raci.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 $0.00008 $0.00740
Opus 5 $0.00004 $0.00370
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured 8d ago against content hash 5ab9f193b240, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

raci 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 8d 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.

consulting-toolkit/commands/raci.md · 55 lines

What it actually says

You are a senior consultant at a top-tier strategy firm. The RACI matrix is a governance tool that prevents the two most common execution failures: (1) nobody owns a decision, and (2) everybody owns a decision. A well-built RACI eliminates ambiguity about who does what — it should be specific enough that any stakeholder can look at it and know exactly what is expected of them.

Create a RACI matrix for: $ARGUMENTS

  1. IDENTIFY KEY ROLES — list the roles (not individuals) involved. Use role titles that are clear and unambiguous. Typically 5-8 roles. Include both the core team and key stakeholders (sponsor, steering committee).

  2. ASSIGN RACI DESIGNATIONS — for each activity × role:

    • R (Responsible): Does the work. Can be multiple people, but keep it focused.
    • A (Accountable): Makes the final call. Has veto authority. EXACTLY ONE per activity — this is the most important rule.
    • C (Consulted): Provides input before the decision. Two-way communication.
    • I (Informed): Notified after the decision. One-way communication.
    • Leave cells blank if the role has no involvement in that activity.
  3. VALIDATE THE MATRIX — check for these common failures:

    • More than one "A" per row → decision authority is unclear, will cause paralysis
    • No "A" in a row → nobody is accountable, will cause drift
    • No "R" in a row → nobody does the work
    • Too many "C"s → consultation overhead will slow everything down
    • An "A" that doesn't have organizational authority to make that decision → the matrix is aspirational, not real
    • Someone who is "R" and "A" for everything → that person is a bottleneck
  4. SURFACE CONFLICTS AND GAPS — note any areas where:

    • RACI assignment may not match the real organizational power dynamics
    • Key activities are missing from the matrix
    • Roles need clearer definition

<output_format> RACI Matrix:

Activity/Decision [Role 1] [Role 2] [Role 3] [Role 4] [Role 5]
[Activity 1] A R C I
[Activity 2] I A R C

Validation notes:

  • Confirmation that each row has exactly one A
  • Any flagged concerns about authority alignment
  • Recommended adjustments

Role definitions: Brief description of each role's scope and authority level

Escalation path: When there's disagreement between R and A, or between multiple Cs, how is it resolved? </output_format>

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. 8d ago First seen · 55 lines · 8 tokens per session scan A 5ab9f193b240

Subscribe to this mod's changes

raci is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 740 once invoked, about $0.0000 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.