io.github.zz-plant/ambit

The actions a capability confers and whether each may be performed: read a repository yes, merge to its default branch no. Omit capId for all. To ask before acting, use ambit_can.

The domain of each capability, from the graph: institutional (needs an authority holder), economic (a budget), cognitive (a person), physical (a device).

The audit trail: a run end to end, a proposal's steps, approval and result, or one person's approvals and interventions. target: run id, proposal id, human name, or days.

Which reached capabilities may run unattended and which need approval. Being able to act is not permission to. Pass detail: true for every grant.

Record that a task was blocked by a missing capability. The same deficit hit repeatedly is infrastructure that should exist.

The capabilities the most others depend on: where an improvement pays most and a loss costs most.

What this environment is, before you touch it: reached and proven, failing, waiting on a person, recently blocked, worth reaching next, and what changed since the last briefing. Read once at session start. Also ambit://briefing.

Standing budgets: what may be spent, on what, and what is left this period. A spend past a ceiling is refused until the period turns over. A person sets one.

Ask before running a tool you have not used this session. yes: act. ask: put it to the person. no: do not retry it under another name. Also returns the reason, what is missing and the budget left. Probes nothing. A no files the deficit.

Find capabilities by domain or name. Returns the ids the other tools take.

The ways to acquire a capability (build, buy, subscribe, delegate, hire) compared by setup, one-time and recurring cost, privacy, verification and rollback.

Combos the graph can already support: every prerequisite in place, with a confidence.

The session briefing as one block of prose, the text ambit_briefing returns with text: true.

What revoking each credential would end. Providers that present the same credential fail together.

Capabilities not touched for long enough to doubt, with days since the last config change.

Recurring capability deficits, worst first: which missing capabilities keep stopping different work.

Per domain, what was recently practiced, improved or regretted, from the last 50 outcomes.

How much work still runs through the human, and which interventions are reducible: recurring approvals and permission blocks are infrastructure shaped like a person. days: window (default 7).

Declared costs and goal values: attention value per hour, recurring and purchase costs, what each goal is worth.

Verification history of one capability: what was tried, when, and whether it passed.

Route a goal, in words, to the capabilities that cover it: ranked, each with its plan delta.

One goal's economics (occurrence rate, success value, failure cost), matched by id or name.

Domain health scores.

What would stop, and what would only lose a provider, if a capability went away.

Close the open incident run for a service with its outcome. MTTR is the ledger's own elapsed time.

Probe the hosts the infrastructure manifest names and open an incident run per offline service, with the authority decision for recovery (restart ALLOW, CONFIRM or DENY).

Every recorded frontier observation: how the system's capacity for action has changed over time.

Near-miss combos: one or two prerequisites away, with high existing maturity.

The capabilities worth reaching next: why, cost, and the command that proposes each. Ranked by what has blocked work once the ledger has data, by leverage per setup hour before.

What may be done to a particular thing, and what is proved about doing it there. Evidence about one repository says nothing about another.

Ranked changes worth making, from recurring human burden in the ledger priced by attention. by: attention (default), cash, roi, reliability, frontier. budget (dollars): the best combination within it.

One ranked opportunity in full: burden, proposed capability, acquisition, expected effect, payback, confidence.

The ways to reach a capability compared by setup time, risk and lock-in: which steps are config changes that can be undone, and which are installers that cannot.

Drafts waiting on a person, each with its cost, what it bills and what it unlocks. Surface them together: a batch is one interruption.

What is missing for a capability, in the order it must be closed, and which steps need a person.

Across imported federation receipts: burden that recurs in several environments, person-specific single points of failure, and (with budget) where spend gains most. Never merges.

What each person prefers, and which plans would fight it (local or hosted, one-off or recurring). Pass who for one person.

What this person has approved and refused, by trait: local or hosted, one-off or recurring. Three decisions make a trait; one that went both ways is contested.

Authority thresholds: which grants may widen on evidence, how much each still needs, what was promoted or put back. A person sets one; an agent only reads this.

One proposal in full, with its steps and simulated frontier.

Every proposal drafted so far, newest first.

Draft a reviewable acquisition: ordered steps, the alternative chosen and its trade-offs, the simulated result. Nothing executes until a person approves it, and only reversible config patches can then be applied.

Report a tool failure you just hit as the runtime reported it: exit code, error text or kind. Ambit classifies it, attributes it to a capability where it can, and keeps it either way.

Put a skill you wrote on the map: an id, the capability it supplies, and a read-only command that proves it works. The check runs at once, so the skill arrives proven or honest about failing.

Which unreached capabilities could be acquired without a person and which need hands. apply refuses a step with no inverse, so this is also what an agent cannot do alone.

Realized ROI of an applied proposal: interventions, hours, attention dollars and reliability before and after, against its prediction. Writes the observation back.

Every applied proposal's observed hours and dollars saved per year, and forecast accuracy: the cumulative headline.

Start a work run. Returns the run id every later telemetry call attaches to. The run stays open until run_end.

Close a work run with its outcome, and the value of that outcome in cents when known.

What a scope covers and what it does not. For a target (repo:owner/name, device:nuc, svc:ollama): every grant, whether it covers the target, and the effective mode.