Open source · CC BY 4.0 · Free

Ship agents your organization can actually own.

The auxfirst skill scores every action an agent can take, caps its autonomy at the hottest dimension, and writes the mandate, exception handling and owner’s manual behind it. Most agent guidance answers “can the model do this?” This answers the question that actually blocks production.

Install in Claude Code
/plugin marketplace add auxfirst/auxfirst-skill-global
/plugin install auxfirst@auxfirst
TypeClaude skill · plugin
LicenseCC BY 4.0
PriceFree, forever
Built fromThe auxfirst canon
What it does

One question, answered the same way every time.

Given an action this agent can take, what does the team owe before it is allowed to take it unsupervised?

You give it an agent — a copilot, an automation, a workflow that writes to a system of record. It gives back written artifacts: a scored action inventory, a mandate with an enforcement mechanism on every row, exception handling with named recipients and deadlines, and a readiness verdict out of 24.

It works per action, never per agent. An agent that can do nine things has nine answers, and averaging them is the exact mistake the skill exists to prevent.

The one rule everything hangs from

An action is as hot as its hottest dimension.

No averaging. Four cool dials never buy back one hot one — a perfectly reversible, narrow, internal action that signs a contract is still a contract. This single rule is what stops “but it’s mostly fine” from shipping a disaster.

Worked example · “send a routine invoice to a client”
Reversibility1
Blast radius0
Exposure3
Commitment3
Authority1

Three dials are cool. The action is still HIGH — it leaves the building and asks for money.
A team scoring by average calls this low-medium and ships it on auto-run.

The core loop

Nine steps. Five of them mechanical.

Steps one to five are lookups the skill runs for you — there is a script, because hand lookups quietly average. Steps six to nine are where the judgment lives, and the skill walks you through them.

  1. List the verbs. What can this agent actually do?
  2. Score each verb on five dimensions, 0–4.
  3. Band take the highest single score. That is the heat band.
  4. Cap the band sets the maximum permitted autonomy mode.
  5. Owe the mode sets the required patterns and supervision primitives.
  6. Write the mandate, action by action.
  7. Except decide the behavior for each failure mode.
  8. Evaluate against the ten heuristics before ship.
  9. Check the twenty-four questions before calling it production.
What’s in the box

A skill, six references, three templates, one script.

The skill.

A single SKILL.md carrying the procedure, loaded only when the work calls for it.

Six references.

Heat ladder, heuristics and patterns, owner’s manual, workflow readiness, production check, anti-patterns.

Three templates.

Mandate, autonomy map and owner’s manual — the artifacts you hand to engineering and to the board.

One script.

heat.py scores an action and returns the band, the autonomy cap and what that mode obliges you to build.

Twenty evals.

A trigger-eval set, because the description is the whole triggering mechanism and guessing is not a test.

The canon.

Everything traces to published, dated auxfirst material. Nothing in the skill is unsourced.

Who it’s for

Two people, and they need different things.

If you build agents.

You install it and it stays out of the way until the work needs it — then it turns a vague autonomy argument into a table you can implement against.

  • Replaces “semi-autonomous” with an enforceable per-action mandate
  • Names the mechanism for every boundary, so nothing lives only in a prompt
  • Gives security review the artifacts it will ask for anyway

If you answer for agents.

You are the named human when something goes wrong. This gives your teams one vocabulary and one bar, so agent nine is as defensible as agent one.

  • A readiness verdict out of 24 you can ask any team for
  • Four production rules that work as gates, not aspirations
  • Capability and supervision reported separately — the gap is the finding
What it does not do

It will not tell you an agent is safe.

It is not about prompts, models, retrieval or cost. Those are real problems and belong elsewhere. This assumes the agent can do the task and asks whether the organization can own it.

It will not give you a single score. Capability and supervision are reported separately and never combined, because the gap between them is the finding. An agent that can do a great deal and can be supervised very little is the specific thing worth knowing, and one number would hide it.

It tells you whether the accountable human can see, approve and undo what the agent did. That is a different claim from safety, and it is the only one a document can honestly support.

Where it comes from

Assembled from work that was already published.

Every component has a longer canonical treatment. The skill is the operational compression; these are the arguments.

Free to use. Free to fork.

CC BY 4.0 — take it, adapt it, ship it inside your own governance. Keep the attribution and tell us what broke.