agents/AGENTS-claude.md

@@ -1,6 +1,6 @@
 @./AGENTS.md
 
-## Firmenwissen (onyx & thicket)
+## Firmenwissen (onyx)
 
 - For questions about internal processes, tools, or "wie machen wir X
   bei Seibert", check the company knowledge first (skill `onyx`).
@@ -10,10 +10,9 @@
   (unexpected spaces, differently worded titles). Use direct
   Confluence CQL only for precise lookups where space or title is
   already known.
-- **Thicket direct only for people lookups** (role, team, email) —
+- Pick the mode by use case (see the skill's mode table): `answer` for
-  its other sections are thin, use onyx there.
+  simple factual questions (cheap on context), `search` when you need
-- Default mode `answer`; `search` only when you need the source text
+  the source text itself — always cite source links.
-  itself — always cite source links.
 
 ## Subagents
 

agents/AGENTS.md

@@ -52,62 +52,18 @@ Treat vague input and question-back responses critically, not as instructions.
 
 ## Team memory (cognee)
 
-cognee is a real memory, not an archive: unlike `MEMORY.md` it is **not**
+- **Store memories in cognee aggressively and on your own** (skill `cognee`) —
-injected automatically, so it only works if you fetch from it and write to it
+  announce it briefly, don't ask first. Save solved problems, decisions,
-on your own. The rules below are events, not attitudes — check them when the
+  reusable infra facts, and lessons learned as soon as they emerge.
-event happens, not "when it feels right".
+- **Routing:** anything concerning team IT (Seibert IT-Infra — ISAC/bw,
-
+  monitoring, INFRA-Board, shared services, servers, team processes) goes to
-### Read: `recall` before you start
+  the team bucket via `remember --team`. Everything else (personal
-
+  preferences, workflow feedback, context only relevant to me) goes to the
-Run `recall` **before the first tool call**, not after you are already deep in
+  personal dataset (plain `remember`).
-the task, when any of these is true:
+- Before deep-diving a larger task or a recurring-looking problem, `recall`
-
+  relevant prior knowledge first.
-- the task touches infrastructure, a server, a service, a ticket or a tool
+- Avoid duplicates: on recurring topics `recall` before saving; never store
-  we run ourselves
+  secrets, credentials, or customer-personal data.
-- an error looks like it could have happened before ("this smells familiar")
-- you are about to pick between options where a decision may already exist
-- the task will plausibly take more than a handful of tool calls
-
-`recall <question>` — no flags. It reads every readable dataset including the
-team one. `--team` exists on `remember` only; on `recall` it is a usage error,
-and `--dataset team-it` fails too because the team dataset is shared rather
-than owned (it would need its UUID). Neither is needed: plain `recall` covers
-everything.
-
-Treat what comes back like a colleague's note: useful, possibly outdated. If a
-memory names a file, flag or host, verify it still exists before acting on it.
-
-### Write: `remember` at these moments
-
-Announce it in one line, never ask first. Write **as the insight appears**, not
-at the end of the session — by then the detail that made it worth saving is
-gone.
-
-- a bug is fixed and the cause was **not** visible in the code (config,
-  limits, environment, an API that lies)
-- a decision is made and an alternative was rejected — save the *why*, that is
-  what the code cannot tell later
-- a measurement contradicts an assumption, mine or yours
-- you correct me, or I correct myself after being wrong
-- a tool, API or service behaves differently than its docs claim
-
-What does **not** belong there: anything the repo already records, anything
-that only matters inside this one conversation, and never secrets,
-credentials or customer-personal data.
-
-### Routing and hygiene
-
-- **Team bucket** (`remember --team`): everything concerning team IT — Seibert
-  IT-Infra, ISAC/bw, monitoring, INFRA board, shared services, servers, team
-  processes. Ask yourself: would a colleague hitting this next month benefit?
-- **Personal dataset** (plain `remember`): my preferences, workflow feedback,
-  context that is only relevant to me.
-- On recurring topics `recall` first and **extend the existing note instead of
-  adding a second one** — two notes on one topic are worse than none, because
-  the older one keeps surfacing.
-- Write notes that answer a question, not headlines. Include the concrete
-  numbers, the error message verbatim, and the fix. A note that says "there
-  was a problem with X" costs more time than it saves.
 
 ## Sandbox