A guide for using typed decision models that answer constrained questions inside software. The answers can inform a separate, rule-based process, but they do not replace permissions or action controls.

Use it to design and evaluate decision models for routing, ranking, guardrails, calibration, app-control loops, or private model operation.

It helps keep model judgments separate from business rules, authorization, side effects, confirmation, and rollback.

system-one — Skill for Claude Code and Codex by magnus919/agent-skills

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 magnus919/agent-skills --skill system-one

Clone the repo

git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin system-one — /plugin install system-one after adding the marketplace above.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/magnus919/agent-skills/system-one/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/system-one)

Your own site

<a href="https://agentmods.dev/skills/magnus919/agent-skills/system-one"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/system-one/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/magnus919/agent-skills/system-one"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/system-one.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,290 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.

Model	Per session	Once invoked
Fable 5.1	$0.00128	$0.03290
Opus 5.5	$0.00051	$0.01316
Sonnet 5.5	$0.00026	$0.00658
Haiku 4.5	$0.00013	$0.00329

Measured 3d ago against content hash f42c069e05cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

system-one 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.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/batch_request_shape.py, scripts/build_decision_battery_v2.py, scripts/cascade_economics.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

system-one/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System One decision models

Use a model for a constrained judgment, not for permissions or side effects:

authorized state + trusted typed questions -> validated model answers
-> deterministic policy -> act / wait / review / abstain -> observed outcome

Keep hard business rules, authority checks, thresholds, action execution, confirmation, and rollback in code or human control. A legal response shape does not imply a correct judgment; a high probability is not permission.

Start here

Inspect the real application's state source, action boundary, tests, and deployment before changing it. Preserve existing deterministic/no-key behavior unless explicitly changing it is in scope.
Fill templates/decision-contract.md: trusted state, question IDs/types, allowed answers, unknown/review lane, side effects, owner, deadlines, and rollback. For tool control, also use templates/action-control-contract.md. New to this model class? Start with references/worked-decision-pilot.md to choose one bounded decision, then use references/concepts-and-patterns.md for primitive semantics and composition.
Open only the matching reference below. Keep exact question instructions, criteria, state paths, and thresholds in trusted configuration, not user-supplied state. IDs are for application code; TypeSafe documents that Jev does not send question IDs to the model, so put complete judgment meaning in each instruction. Other providers may have different contracts. For question wording or candidate extraction, read references/question-design.md.
Validate response IDs, types, option sets, distributions, score rubric, and finite values before policy code; record returned model/version and enforce the pinned deployment identity. Treat malformed, unavailable, stale, or low-evidence results as the specified fallback.
Verify on representative held-out data and the actual delivery boundary; record provider/model, question/policy revision, outcome, and failure lane without raw secrets or unnecessary personal data.

Read the full file on GitHub · 183 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago Changed · +3 lines · +8 tokens per session f42c069e05cd
4d ago Changed · +1 lines b8eff193c7db
8d ago Changed · +4 lines aff68407f3b8
11d ago Changed · +7 lines 44fd3f30d09a
13d ago Changed · +3 lines · +6 tokens per session 30b99437ae87
17d ago Changed · +11 lines c766d05c4f57
21d ago Changed · +21 lines · +24 tokens per session 9716cc34181d
22d ago Changed · +5 lines · +4 tokens per session 40eaa37d9dd3
22d ago Changed · +31 lines 0e45a0ed22e5
24d ago First seen · 97 lines · 86 tokens per session scan A d451adc5e092

Subscribe to this mod's changes

system-one is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 128 tokens to every session and 3,290 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-23.

Building agents LLM agent-skills agentskills ai-agents automation

cocoreview

CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].

Snowflake-Labs/cocoplus · 57 tokens

spec

Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.

Snowflake-Labs/cocoplus · 53 tokens

discuss

Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.

Snowflake-Labs/cocoplus · 54 tokens

cocoharvest

Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…

Snowflake-Labs/cocoplus · 68 tokens

cocoscout

Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.

Snowflake-Labs/cocoplus · 59 tokens

bloom

Run a structured four-question working-backwards dialogue before $spec — commits the developer to the outcome (beneficiary, core capability, constraints, press release) before specification begins, anchoring all downstream phases to the original intent.

Snowflake-Labs/cocoplus · 47 tokens