prove-an-index-cannot-show-what-it-must-not
Reconcile what was indexed against what exists, then test the permissions in both directions — including one query for the most sensitive content in scope.
Procedure
- start start. Goes next to s1
- check The counts match what the source holds. Goes on_fail to s3; next to s2
- decision Is any gap explained?. Goes if unexplained to s3; if default to s4
- action Work the four causes in order, RO (read-only). Goes retry to s1; next to s9
- action Test that the right people see it, RO (read-only). Goes on_fail to s9; next to s5
- action Query the most sensitive thing in scope, RO (read-only). Goes on_fail to s9; next to s6
- decision Did anything forbidden come back?. Goes if leaked to s9; if default to s7
- check A citation opens the item it names. Goes on_fail to s9; next to s8
- action Publish how stale it may be, RO (read-only). Goes on_fail to s9; next to __end_success
- escalate Stop the rollout. Terminal
- end success. Terminal
Open the graph on its own page — larger, printable, and an address you can send.
Walk it without running it — you answer what your environment would answer, and the path, the capabilities, the approvals and the distance back to an undo come out of the document. Nothing executes; there is no Run button here and there will not be one.
Trust
T2 · attested 2026-10-11 · runbooks.directory
Nobody has attested this record. That is the ordinary case: T2 is what the catalog can check on its own, and T3 needs somebody to run the procedure and sign for it.
- Link liveness has not been checked: it needs a network and the catalog builds without one. Run
pnpm gates --onlinewhere there is one.
Steps
s1check — The counts match what the source holdss2decision — Is any gap explained?s3action — Work the four causes in order (read-only)s4action — Test that the right people see it (read-only)s5action — Query the most sensitive thing in scope (read-only)s6decision — Did anything forbidden come back?s7check — A citation opens the item it namess8action — Publish how stale it may be (read-only)s9escalate — Stop the rollout
Capabilities
This is a privilege request. Check it against your own allowlist before running.
Provenance
- Source
- https://github.com/microsoft/ai-agent-runbooks/blob/083f33eec889/02-patterns/Copilot-Connector-Knowledge-Onboarding/Copilot-Connector-Knowledge-Onboarding-Runbook.md
- Fetched
- 2026-09-04
- Source last checked
- not since it was captured on 2026-09-04 — recorded as
current - Licence
- MIT
- How it got here
- Rewritten here from the source above, under its licence. The words and the steps are this catalog's; the procedure it describes is not this catalog's invention, and the source is where to check it.
- Highest risk in this procedure
- reversible-write
Take it with you
- SKILL.md — the record as an Agent Skills file
- workflow.yaml — Open Workflow DSL 1.0.3, for a runner
- record.json — the catalog's own JSON
- graph.svg — the graph, standalone
Run it under supervision
Runs here, on your machine, under supervision: every step is proposed before it happens, an approval gate stops for you, and a failed expectation goes where the procedure says rather than on to the next step. Nothing is sent anywhere. To supervise an agent that is doing the work instead, runbooks hook sits in its tool-call path.
npx @runbooks/cli run adapted/prove-an-index-cannot-show-what-it-must-not@1.0.0 --as "$(whoami)" \
--input expected_items=<how many items the source was inventoried as holding> \
--input sensitive_example=<the most sensitive content in scope, named before testing starts>