docker reads, one local model, one kept artifact.
The whole workflow
nika check passes it on nika {STATUS.version} (exit 0 · permits
declared · 0 hints). Save it as docker-health-report.nika:
Why the exec tasks are arrays
Writeshell: "docker ps | grep Up" and nika check refuses to bless
the boundary:
permits.exec: ["docker"] is a boundary the checker
can actually prove. Transforms that would have lived in | grep | awk
belong in extract: bindings and nika:jq instead.
What the audit says before a token is spent
nika {STATUS.version}; the rows that only say ✔ for checks this file does not exercise are left out.
Two things worth noticing:
- The two
dockerreads run in parallel (wave 1) — the scheduler proved it from thewith:bindings, nobody ordered it. - The cost line practices the honesty rule: a local model is unpriced compute, not « free » — the report says the total has no ceiling and names why (no catalog price for a local model); it never rounds unknown to $0.
Run it
docker reads side by side (∥, the same wave), then the model call, which
takes as long as your model needs, then the write. The total reads
unpriced, never $0.00: nothing in the catalog can meter a model on your
own machine. Rehearse the whole file first with
nika run docker-health-report.nika --model mock/echo: the docker reads run
for real and the mock echoes the prompt instead of calling a model.
docker-health.md then holds the model’s prose, and the run left a
hash-chained journal you can prove later:
When the daemon is down
The failure is part of the design. With Docker stopped, the same run fails honestly and early — the model is never called, nothing is spent, and the card hands over. Captured onnika {STATUS.version}:
Take it further
- Gate an action on the report — add an
agent:task allowed onlynika:done, or awhen:gate on a structureddiagnoseoutput, and the workflow can act on unhealthy containers, still inside the declared boundary. See patterns. - Schedule it — the file is the artifact: cron or CI runs
nika run; when journaling is enabled, inspect and verify the evidence the execution leaves behind. - Structured instead of prose — give
diagnoseaschema:and the report becomes typed data downstream tasks can branch on. See testing for pinning it with a golden.
The two
exec tasks carry the repo’s exec ledger (the header
comment): every surviving exec: names why no builtin or MCP tool
covers it yet, and what would remove it. When a Docker MCP server enters
your stack, invoke: replaces both reads and the ledger empties —
that is the native-first law working as intended.