Redact at every capture point

One unscrubbed sink undoes all the others.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule

Apply redaction everywhere content is persisted or surfaced. Route through scrub() at: log emission (wrap the logger), trace/span attribute capture (the observability scrubber), session record writes, memory writes, error/exception reports (stack traces and locals can carry secrets), and any content shown in the UI beyond the live session. Critically, also scrub MODEL-FACING content where the agent does not need the raw value: tool results containing credentials get redacted before entering context (the agent reasons fine about '[REDACTED:api-key]'). Enforce via a single choke: capture functions must accept only pre-scrubbed content, or call scrub internally. Audit the codebase for any direct writes to these sinks that bypass the wrapper.

Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

Redaction enforced at every persistence and display point.

Should NOT happen

An existing feature broke
A button only logs to console
Data disappears after refresh
Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Your notes for this step

Track what changed, failed, or needs follow-up. Notes export with the flow.

Pass the Verify Gate to complete this step

Verify before continuing

Do not move on until every check is true. The complete button stays locked until then.

All sinks route through scrub()Model-facing tool output scrubbed where raw secrets are unneededBypass paths audited and closed

Do not continue if…

! Secrets in plaintext logs and traces, one breach from disaster
! Redacting logs but leaving secrets in session records or memory files
! Passing real credentials through the model context 'because it is convenient'
! Assuming no leaks without ever scanning stored artifacts

If the AI messes this up

Use this when:

- it only made visual forms or placeholder UI
- buttons do nothing or only log to console
- data is not persisted - state disappears on refresh
- something that worked before is now broken

Use this when the AI fakes progress or breaks the feature. It forces a real fix.

Secrets appear in one sink (e.g. error reports). That sink bypasses the wrapper - route it through scrub() at capture; exception handlers are a classic miss because they form strings on a separate path.