apply-raci-matrix

apply-raci-matrix is a skill for Claude Code from jeffreytse/grimoire-core. It costs 81 tokens per session (1,746 once invoked), scanned A, original, MIT.

A responsibility chart that assigns who does a task, who owns the decision, who gives input, and who is kept informed.

In plain words
What is it for?
Use it to clarify responsibilities for projects, recurring processes, and important decisions.
Why use it?
It prevents work from stalling because ownership is unclear and limits unnecessary debate over decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Use it to clarify responsibilities for projects, recurring processes, and important decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-raci-matrix
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 jeffreytse/grimoire-core --skill apply-raci-matrix
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

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 apply-raci-matrix

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-raci-matrix/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-raci-matrix)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-raci-matrix"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-raci-matrix/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for apply-raci-matrix

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-raci-matrix"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-raci-matrix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,746 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 $0.00081 $0.01746
Opus 5 $0.00041 $0.00873
Sonnet 5 $0.00016 $0.00349
Haiku 4.5 $0.00008 $0.00175

Measured 7d ago against content hash c256defab9f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

apply-raci-matrix 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/business/operations/skills/apply-raci-matrix/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply RACI Matrix

Assign each task or decision exactly one Responsible doer and one Accountable owner, and explicitly limit who is Consulted (two-way input sought before the decision) versus merely Informed (notified after it) — because unclear ownership, not lack of effort, is what causes tasks to stall and decisions to be second-guessed by people who were never meant to have a vote.

Why This Is Best Practice

Why best: Most task and decision breakdowns in organizations are not caused by anyone failing to do their job — they're caused by nobody being clearly assigned the job of deciding or doing in the first place, or by too many people being given an implicit veto through vague "everyone should weigh in" norms. RACI's specific contribution is forcing exactly one name into the Accountable role per task — not zero, not several — because shared or absent accountability is what produces stalled decisions and diffused responsibility, and forcing exactly one Responsible doer per task prevents the common failure where a task assigned to "the team" gets done by no one in particular.

PMBOK Guide and matrix-management practice: The RACI matrix — Responsible, Accountable, Consulted, Informed — is documented as standard project-management practice in the Project Management Institute's PMBOK Guide, one of the most widely adopted project-management standards globally. Its four roles are specifically and narrowly defined: Responsible is the person who does the work; Accountable is the single person ultimately answerable for the task being done (and who must approve it); Consulted are people whose input is sought two-way before the decision is finalized; Informed are people who are notified one-way after the decision or task is complete, with no expectation of input. The matrix's discipline comes specifically from restricting Accountable to exactly one name per row — multiple "accountable" parties reintroduce the diffused-ownership problem the tool exists to solve.

Read the full file on GitHub · 63 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. 7d ago First seen · 63 lines · 81 tokens per session scan A c256defab9f7

Subscribe to this mod's changes

apply-raci-matrix is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 81 tokens to every session and 1,746 once invoked, about $0.0004 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 2026-09-03.