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.
npx agentmods add skills/tupe12334/instinct/racinpx skills add tupe12334/instinct --skill racigit clone --depth 1 https://github.com/tupe12334/instinctWrote 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.
[](https://agentmods.dev/skills/tupe12334/instinct/raci)<a href="https://agentmods.dev/skills/tupe12334/instinct/raci"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/raci.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.01744 |
| Opus 5 | $0.00012 | $0.00872 |
| Sonnet 5 | $0.00005 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00174 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RACI Matrix
Overview
RACI assigns one of four roles to every person on every task or decision, eliminating the ambiguity that causes dropped work and duplicated effort. Each row is a task; each column is a person or team.
Person A Person B Person C Person D
Task 1 R A C I
Task 2 A R I C
Task 3 C I R A
- R — Responsible: Does the work. Can be multiple people.
- A — Accountable: Owns the outcome; makes the final call. Exactly one per task.
- C — Consulted: Provides input before the decision or action. Two-way communication.
- I — Informed: Notified after the decision or action. One-way communication.
Role Definitions
R — Responsible
The person or people executing the task. They do the actual work. Multiple Rs are allowed, but each R must have a clearly scoped slice — two Rs with identical scope creates confusion, not coverage.
A — Accountable
The single owner. If the task fails, A answers for it. A has final authority to approve, reject, or change direction. There must be exactly one A per task — two As means no one is actually accountable.
C — Consulted
Their expertise or stake affects the outcome. They must be asked before decisions are finalized. Ignoring a C is a process failure. Keep this list short: Consulted is a cost — it adds latency and coordination overhead.
I — Informed
They need visibility, not a vote. Inform them after the fact. Over-informing is as harmful as under-informing — too many Is means noise, and people stop reading updates.
How to Apply
Step 1 — List all tasks and decisions
Write out every discrete deliverable, decision, or milestone. Be specific. "Design" is not a task. "Approve final UI mockup" is.
Step 2 — List all roles or people
Use roles (Engineering Lead, Product Manager, Legal) rather than names where possible — the matrix survives org changes longer.
Step 3 — Assign R, A, C, I for each task
Fill in the matrix cell by cell. For each task, ask: who does it (R), who owns the outcome (A), who must be asked (C), who must be told (I).
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.
- 4d ago First seen · 119 lines · 23 tokens per session scan A a3ce7a37af27
raci is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 18d ago), licensed MIT. It adds 23 tokens to every session and 1,744 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 2026-08-31.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
thinking-lindy-effect
Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.
thinking-kepner-tregoe
Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.