docs(#608): migrate off .fullsend/customized/skills/ per ADR 0064

AGENTS.md

@@ -80,13 +80,27 @@ stable (non-prerelease) version. Downstream consumers can reference
 
 ## 7. Skill resolution
 
-Skills declared in agent frontmatter `skills:` arrays are resolved at
-runtime from multiple sources in priority order: repo-level
-(`.agents/skills/`), org-level (`fullsend-ai/.fullsend/customized/skills/`),
-and upstream platform (`fullsend-ai/fullsend/skills/`). A skill reference
-in frontmatter is valid even if no matching directory exists in this repo.
-Do not treat missing local skill directories as bugs without first
-verifying the skill does not exist at org or platform level.
+Skills listed in harness `skills:` arrays are resolved at runtime from
+multiple sources in priority order: repo-level (`.agents/skills/`) and
+upstream platform (`fullsend-ai/fullsend/skills/`). A skill reference is
+valid even if no matching directory exists in this repo. Do not treat
+missing local skill directories as bugs without first verifying the skill
+does not exist at platform level.
+
+To override an upstream skill, create a custom harness with `base:`
+composition pointing to the upstream harness and include the replacement
+skill in the `skills:` array. For example, to override `issue-labels`
+for the review agent:
+
+```yaml
+# .fullsend/review.yaml
+base: https://raw.githubusercontent.com/fullsend-ai/agents/<SHA>/harness/review.yaml#sha256=<sha256sum>
+skills:
+  - .agents/skills/issue-labels
+```
+
+See [Custom sandbox image — How to configure](docs/code.md#how-to-configure)
+for how to obtain the `<SHA>` and `<sha256sum>` values.
 
 ### Valid SKILL.md frontmatter fields
 

FEATURES.md

@@ -34,7 +34,7 @@ Before writing code, answer:
 |---------|-------------|---------|
 | **Environment variable** | Runtime behavior toggle, simple values, specific to one agent — per ADR 0080 (fullsend-ai/fullsend), this is single-agent behavior tuning rather than a `config.yaml` field. Repo owners set it in their base-derived harness files, overriding via `base:` composition (ADR 0045). Per ADR 0049, it must use an `{AGENT}_` prefix. Per ADR 0081, the CI workflow `env:` block is reserved for infrastructure plumbing (credentials, project IDs, regions) — don't use workflow inputs to set a behavior knob's value, except for values only computable at CI runtime. We recommend picking one surface per option — either an env var or a `config.yaml` option, not both — to avoid two sources of truth. | `TRIAGE_AUTO_CODE` |
 | **`config.yaml` option** | The option should be respected by *every* agent, not just one — no agent-specific prefix, and not configurable via env var. | the cross-repo allow list |
-| **Skill override** | The behavior is best expressed as natural-language instructions to the agent. Repo owners drop a replacement skill in `.agents/skills/`. Org owners override via `base:` composition (ADR 0045) — inherit the upstream harness and add the skill under `skills:` with the same basename as the one being replaced, so the merge dedupes by basename (fullsend-ai/fullsend #5409) and it wins. The older `customized/skills/` overlay in the org `.fullsend` config repo is deprecated by ADR 0064. | `issue-labels` skill |
+| **Skill override** | The behavior is best expressed as natural-language instructions to the agent. Repo owners drop a replacement skill in `.agents/skills/`. Org owners override via `base:` composition (ADR 0045) — inherit the upstream harness and add the skill under `skills:` with the same basename as the one being replaced, so the merge dedupes by basename (fullsend-ai/fullsend #5409) and it wins. | `issue-labels` skill |
 
 Environment variables are the simplest for end users to configure.
 Skills are more flexible — they let repo or org owners override
@@ -133,8 +133,8 @@ agent prompt:
 - [ ] If the env var is agent-specific, consider whether or not it should be
       baked into that skill.  Keep agent-specific logic in the agent prompt;
       keep reusable judgment in the skill.
-- [ ] If you add a new skill, add it to `harness/<agent>.yaml` under
-      `skills:` and to the agent frontmatter `skills:` array.
+- [ ] If you add a new skill, add it to the harness `skills:` array
+      in `harness/<agent>.yaml`.
 
 ## 9. Update documentation
 

docs/review.md

@@ -69,9 +69,21 @@ labels and apply them to PRs during review. This is the same skill used by the
 To overload the built-in skill, create your own `issue-labels` skill in
 `.agents/skills/issue-labels/SKILL.md` and symlink `.claude/skills` to
 `.agents/skills` so it's discoverable by both fullsend and local agent tooling.
-You can also overload it at the org level in your `.fullsend` config repo at
-`customized/skills/issue-labels/SKILL.md`. At runtime, your version replaces
-the upstream default — no other configuration needed.
+To override explicitly, create a custom harness with `base:`
+composition and include the replacement skill in the `skills:` array.
+At runtime, your version replaces the upstream default.
+
+For example, to override `issue-labels` for the review agent:
+
+```yaml
+# .fullsend/review.yaml
+base: https://raw.githubusercontent.com/fullsend-ai/agents/<SHA>/harness/review.yaml#sha256=<sha256sum>
+skills:
+  - .agents/skills/issue-labels
+```
+
+See [Custom sandbox image — How to configure](code.md#how-to-configure)
+for how to obtain the `<SHA>` and `<sha256sum>` values.
 
 See [Customizing with AGENTS.md](https://fullsend.sh/docs/guides/user/customizing-with-agents-md) and
 [Customizing with Skills](https://fullsend.sh/docs/guides/user/customizing-with-skills).

docs/triage.md

@@ -70,13 +70,21 @@ every agent).
 To overload the built-in skill, create your own `issue-labels` skill in
 `.agents/skills/issue-labels/SKILL.md` and symlink `.claude/skills` to
 `.agents/skills` so it's discoverable by both fullsend and local agent tooling.
-At the org level, override via `base:` composition (ADR 0045) — inherit
-the upstream harness and add your skill under `skills:` with the same
-basename (`issue-labels`) as the one you're replacing, so the merge
-dedupes by basename (fullsend-ai/fullsend #5409) and yours wins. The
-older `customized/skills/issue-labels/SKILL.md` overlay in the org
-`.fullsend` config repo (and the per-repo `.fullsend/customized/skills/...`
-equivalent) is deprecated by ADR 0064.
+To override explicitly, create a custom harness with `base:`
+composition and include the replacement skill in the `skills:` array.
+At runtime, your version replaces the upstream default.
+
+For example, to override `issue-labels` via a custom triage harness:
+
+```yaml
+# .fullsend/triage.yaml
+base: https://raw.githubusercontent.com/fullsend-ai/agents/<SHA>/harness/triage.yaml#sha256=<sha256sum>
+skills:
+  - .agents/skills/issue-labels
+```
+
+See [Custom sandbox image — How to configure](code.md#how-to-configure)
+for how to obtain the `<SHA>` and `<sha256sum>` values.
 
 Here's an example that encodes domain-specific labeling rules: