docs: pull Agents docs directly

.gitignore

@@ -23,3 +23,4 @@ bin/
 .transcripts/
 eval/runs/
 docs/superpowers/plans/*.md
+docs/agents/

docs/ADRs/0049-agent-configuration-env-var-convention.md

@@ -25,6 +25,11 @@ decides when a knob should be an `{AGENT}_` env var at all versus a
 which narrows the "CI workflow injection" delivery mechanism to
 infrastructure values.*
 
+*2026-08: References to `docs/agents/<agent>.md` below reflect the original
+layout. Agent documentation now lives in the
+[`fullsend-ai/agents`](https://github.com/fullsend-ai/agents) repository and
+is fetched into `docs/agents/` at build time.*
+
 ## Context
 
 Agents need behavioral knobs — settings that tune *how* they work without

docs/ADRs/0080-config-yaml-vs-agent-env-var-scope.md

@@ -106,9 +106,9 @@ not a placement gap.
 ## Consequences
 
 - Resolves the fullsend-ai/agents#567 ambiguity: `TRIAGE_AUTO_CODE` stays
-  an env var; `docs/agents/<agent>.md`'s Variables table must state how to
-  override it (which harness layer to edit), matching the guidance ADR
-  0049 already expects.
+  an env var; each agent's doc file (in `fullsend-ai/agents`) Variables
+  table must state how to override it (which harness layer to edit),
+  matching the guidance ADR 0049 already expects.
 - `config.yaml` cannot accumulate `{agent}_foo`-style fields — any such
   field is a signal the knob was misplaced.
 - An env var cannot quietly gain a `config.yaml` mirror with its own