feat(cli)!: rename --fullsend-dir to --agent-dir with deprecation alias

docs/cli/agent.md

@@ -23,15 +23,15 @@ Manage agent registrations in fullsend config. Add, list, update, and remove age
 Register an agent in config by URL or local path. URL sources are automatically pinned to a specific commit SHA and annotated with a `#sha256=...` integrity hash. The URL prefix is added to `allowed_remote_resources` if not already present.
 
 ```bash
-fullsend agent add https://github.com/my-org/agents/blob/main/harness/lint.yaml --fullsend-dir .fullsend
-fullsend agent add harness/custom-review.yaml --name my-review --fullsend-dir .fullsend
+fullsend agent add https://github.com/my-org/agents/blob/main/harness/lint.yaml --agent-dir .fullsend
+fullsend agent add harness/custom-review.yaml --name my-review --agent-dir .fullsend
 ```
 
 ### Flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--fullsend-dir` | | Base directory containing the `.fullsend` layout (required) |
+| `--agent-dir` | | Base directory containing agent definitions (required) |
 | `--name` | derived from filename | Explicit agent name |
 
 GitHub blob URLs are resolved to pinned `raw.githubusercontent.com` URLs. Non-GitHub URLs must already contain a commit SHA in the path. Local paths must be relative, must not contain path traversal (`..`), and the file must exist. If an agent with the same name already exists, the command fails.
@@ -41,14 +41,14 @@ GitHub blob URLs are resolved to pinned `raw.githubusercontent.com` URLs. Non-Gi
 List all agents registered in config, showing each agent's name and source.
 
 ```bash
-fullsend agent list --fullsend-dir .fullsend
+fullsend agent list --agent-dir .fullsend
 ```
 
 ### Flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--fullsend-dir` | | Base directory containing the `.fullsend` layout (required) |
+| `--agent-dir` | | Base directory containing agent definitions (required) |
 
 Read-only. Displays a table with `NAME` and `SOURCE` columns. For URL agents, the `#sha256=...` integrity hash suffix is stripped from the displayed source for readability. Disabled agents (`enabled: false`) are included in the listing.
 
@@ -64,15 +64,15 @@ my-lint  harness/my-lint.yaml
 Update a URL-based agent to a new commit SHA and recompute the `#sha256=...` integrity hash. If no SHA is provided, the default branch HEAD is resolved automatically.
 
 ```bash
-fullsend agent update triage --fullsend-dir .fullsend
-fullsend agent update triage a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2 --fullsend-dir .fullsend
+fullsend agent update triage --agent-dir .fullsend
+fullsend agent update triage a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2 --agent-dir .fullsend
 ```
 
 ### Flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--fullsend-dir` | | Base directory containing the `.fullsend` layout (required) |
+| `--agent-dir` | | Base directory containing agent definitions (required) |
 
 Only URL agents can be updated — local path agents have nothing to pin. Non-GitHub URL agents require an explicit SHA argument. The integrity hash is recomputed by fetching the content at the new SHA.
 
@@ -81,29 +81,29 @@ Only URL agents can be updated — local path agents have nothing to pin. Non-Gi
 Remove an agent from config. If the removed agent was the last one using a given `allowed_remote_resources` prefix, that prefix is also cleaned up.
 
 ```bash
-fullsend agent remove triage --fullsend-dir .fullsend
+fullsend agent remove triage --agent-dir .fullsend
 ```
 
 ### Flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--fullsend-dir` | | Base directory containing the `.fullsend` layout (required) |
+| `--agent-dir` | | Base directory containing agent definitions (required) |
 
 ## `agent migrate-customizations`
 
 Scan the `customized/` directory and migrate each override to a config-driven agent. Changes are committed to a branch and delivered via pull request. Use `--dry-run` to preview changes without creating a PR.
 
 ```bash
-fullsend agent migrate-customizations --fullsend-dir .fullsend --dry-run
-fullsend agent migrate-customizations --fullsend-dir .fullsend --repo owner/repo
+fullsend agent migrate-customizations --agent-dir .fullsend --dry-run
+fullsend agent migrate-customizations --agent-dir .fullsend --repo owner/repo
 ```
 
 ### Flags
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--fullsend-dir` | | Base directory containing the `.fullsend` layout (required) |
+| `--agent-dir` | | Base directory containing agent definitions (required) |
 | `--repo` | | Target repository (`owner/repo`) for the migration PR (required unless `--dry-run`) |
 | `--dry-run` | `false` | Show what would change without creating a PR |
 

docs/guides/dev/cli-internals.md

@@ -102,19 +102,19 @@ fullsend
 │   ├── update       <name> [sha]             # Re-pin URL agent to new commit SHA
 │   ├── remove       <name>                   # Unregister agent from config
 │   └── migrate-customizations               # Migrate customized/ → config agents
-│       ├── --fullsend-dir <dir>             #   Base directory with .fullsend layout
+│       ├── --agent-dir <dir>                #   Base directory containing agent definitions
 │       ├── --repo <owner/repo>              #   Target repo for migration PR
 │       └── --dry-run                        #   Preview changes without PR
 ├── lock             [agent-name]              # Pin remote deps to lock.yaml
 │   ├── --all                                #   Lock all harnesses in the harness directory
-│   ├── --fullsend-dir <path>                #   Base directory with .fullsend layout
+│   ├── --agent-dir <path>                   #   Base directory containing agent definitions
 │   ├── --forge <platform>                   #   Lock only this forge variant; omit for all
 │   ├── --update                             #   Force re-resolve even if current
 │   ├── --offline                            #   Reject network fetches
 │   ├── --max-depth <int>                    #   Max transitive dependency depth
 │   └── --max-resources <int>                #   Max total remote resources
 ├── run                                      # Execute an agent in a sandbox
-│   ├── --fullsend-dir <path>                #   Base directory with .fullsend layout
+│   ├── --agent-dir <path>                   #   Base directory containing agent definitions
 │   ├── --target-repo <path>                 #   Path to the target repository
 │   ├── --output-dir <path>                  #   Base directory for run output
 │   ├── --env-file <path>                    #   Load env vars from dotenv file (repeatable)
@@ -153,10 +153,10 @@ The `fullsend agent migrate-customizations` command converts `customized/` direc
 
 ```bash
 # Preview what would change (no PR created)
-fullsend agent migrate-customizations --fullsend-dir .fullsend --dry-run
+fullsend agent migrate-customizations --agent-dir .fullsend --dry-run
 
 # Create a migration PR
-fullsend agent migrate-customizations --fullsend-dir .fullsend --repo owner/repo
+fullsend agent migrate-customizations --agent-dir .fullsend --repo owner/repo
 ```
 
 Migration actions per agent:

docs/guides/user/bring-your-own-agent.md

@@ -386,12 +386,12 @@ description: Org-specific linting rules and conventions.
 
 Test it locally first (see [Testing locally](#testing-locally) for all flags):
 ```bash
-fullsend run code --fullsend-dir .fullsend --target-repo ./my-repo --env-file .env.local
+fullsend run code --agent-dir .fullsend --target-repo ./my-repo --env-file .env.local
 ```
 
 Then register it:
 ```bash
-fullsend agent add harness/code.yaml --name code --fullsend-dir .fullsend
+fullsend agent add harness/code.yaml --name code --agent-dir .fullsend
 ```
 
 Because config-registered agents take precedence over built-in agents on name collision, your `code` agent replaces the default — with all of the base agent's scripts, policies, host_files, and plugins still inherited.
@@ -431,7 +431,7 @@ Before registering, verify your agent works locally. Most agents need additional
 
 ```bash
 fullsend run my-agent \
-  --fullsend-dir .fullsend \
+  --agent-dir .fullsend \
   --target-repo ./my-repo \
   --env-file .env.local
 ```
@@ -452,15 +452,15 @@ The examples above show customizing built-in agents via `base`. If you've built
 # Add (auto-pins URL with SHA256):
 fullsend agent add \
   https://github.com/fullsend-ai/agents/blob/main/harness/triage.yaml \
-  --fullsend-dir .fullsend
+  --agent-dir .fullsend
 
 # Add local:
-fullsend agent add harness/my-agent.yaml --name my-agent --fullsend-dir .fullsend
+fullsend agent add harness/my-agent.yaml --name my-agent --agent-dir .fullsend
 
 # List / update / remove:
-fullsend agent list --fullsend-dir .fullsend
-fullsend agent update triage <sha> --fullsend-dir .fullsend
-fullsend agent remove triage --fullsend-dir .fullsend
+fullsend agent list --agent-dir .fullsend
+fullsend agent update triage <sha> --agent-dir .fullsend
+fullsend agent remove triage --agent-dir .fullsend
 ```
 
 ### Per-repo config (`.fullsend/config.yaml`)
@@ -513,12 +513,12 @@ If you have existing files in `customized/`, the `fullsend agent migrate-customi
 
 Preview what would change:
 ```bash
-fullsend agent migrate-customizations --fullsend-dir .fullsend --dry-run
+fullsend agent migrate-customizations --agent-dir .fullsend --dry-run
 ```
 
 Run the migration (creates a PR with the changes):
 ```bash
-fullsend agent migrate-customizations --fullsend-dir .fullsend --repo owner/repo
+fullsend agent migrate-customizations --agent-dir .fullsend --repo owner/repo
 ```
 
 The tool classifies each override and takes the appropriate action:

docs/guides/user/building-custom-agents.md

@@ -482,7 +482,7 @@ jobs:
           set -euo pipefail
           mkdir -p "$GITHUB_WORKSPACE/output"
           fullsend run my-agent \
-            --fullsend-dir "$GITHUB_WORKSPACE/.fullsend" \
+            --agent-dir "$GITHUB_WORKSPACE/.fullsend" \
             --target-repo "$GITHUB_WORKSPACE/target-repo" \
             --output-dir "$GITHUB_WORKSPACE/output"
 

docs/guides/user/running-agents-locally.md

@@ -132,7 +132,7 @@ can also use `--keep-sandbox` to debug failures (but remember to remove them).
 installing them all, you can use a container image fullsend publishes —
 see [Run from a container](#run-from-a-container) below.
 
-**Note**: to run custom agents set `--fullsend-dir` to the directory where your
+**Note**: to run custom agents set `--agent-dir` to the directory where your
 custom agent definitions exist.
 
 ### Triage agent
@@ -147,7 +147,7 @@ GITHUB_ISSUE_URL=https://github.com/{org}/{repo}/issues/{issue_num}
 
 ```bash
 fullsend run triage \
-  --fullsend-dir /tmp/fullsend-agents/ \
+  --agent-dir /tmp/fullsend-agents/ \
   --target-repo /tmp/target-repo/ \
   --env-file fullsend-gcp.env \
   --env-file fullsend-triage.env
@@ -169,7 +169,7 @@ REPO_FULL_NAME="{org}/{repo}"
 
 ```bash
 fullsend run review \
-  --fullsend-dir /tmp/fullsend-agents/ \
+  --agent-dir /tmp/fullsend-agents/ \
   --target-repo /tmp/target-repo/ \
   --env-file fullsend-gcp.env \
   --env-file fullsend-review.env
@@ -196,7 +196,7 @@ GITHUB_WORKSPACE=/tmp/
 
 ```bash
 fullsend run code \
-  --fullsend-dir /tmp/fullsend-agents/ \
+  --agent-dir /tmp/fullsend-agents/ \
   --target-repo /tmp/target-repo/ \
   --env-file fullsend-gcp.env \
   --env-file fullsend-code.env
@@ -222,13 +222,13 @@ to skip re-resolution when the harness has not changed since the lock was
 generated. Generate or update a lock file with:
 
 ```bash
-fullsend lock code --fullsend-dir /path/to/.fullsend
+fullsend lock code --agent-dir /path/to/.fullsend
 ```
 
 To lock all harnesses in the directory at once:
 
 ```bash
-fullsend lock --all --fullsend-dir /path/to/.fullsend
+fullsend lock --all --agent-dir /path/to/.fullsend
 ```
 
 When `--forge` is specified, only that platform variant is locked. When omitted,
@@ -258,7 +258,7 @@ Example:
 
 ```bash
 fullsend run triage \
-  --fullsend-dir /tmp/fullsend-agents/ \
+  --agent-dir /tmp/fullsend-agents/ \
   --target-repo /tmp/target-repo/ \
   --env-file fullsend-gcp.env \
   --env-file fullsend-triage.env \
@@ -296,7 +296,7 @@ podman run --rm -it --network=host \
   -v "$PWD:/work" \
   ghcr.io/fullsend-ai/fullsend-runner:latest \
   run triage \
-    --fullsend-dir /tmp/fullsend-agents/ \
+    --agent-dir /tmp/fullsend-agents/ \
     --target-repo /tmp/target-repo/ \
     --env-file fullsend-gcp.env \
     --env-file fullsend-triage.env
@@ -356,7 +356,7 @@ git clone https://github.com/{org}/{target-repo} /tmp/target-repo
 cp -r /tmp/target-repo/.fullsend/customized/. /tmp/agents/
 ```
 
-When you execute `fullsend run`, pass `--fullsend-dir` as `/tmp/agents/`.
+When you execute `fullsend run`, pass `--agent-dir` as `/tmp/agents/`.
 
 ## Platform notes
 

docs/plans/agent-extraction-to-agents-repo.md

@@ -607,7 +607,7 @@ agents resolve correctly and show source as the agents repo URL
 instead of scaffold:
 
 ```bash
-fullsend agent list --fullsend-dir .
+fullsend agent list --agent-dir .
 ```
 
 Expected output: all 6 agents listed with their agents-repo URLs,

docs/plans/agent-registration.md

@@ -135,10 +135,10 @@ Both also seed default `AllowedRemoteResources`:
 **File:** `internal/cli/agent.go` (new)
 
 ```
-fullsend agent add <url-or-path> [--name <name>]
-fullsend agent list [--fullsend-dir <path>]
-fullsend agent update <name> [<sha>] [--fullsend-dir <path>]
-fullsend agent remove <name> [--fullsend-dir <path>]
+fullsend agent add <url-or-path> [--name <name>] [--agent-dir <path>]
+fullsend agent list [--agent-dir <path>]
+fullsend agent update <name> [<sha>] [--agent-dir <path>]
+fullsend agent remove <name> [--agent-dir <path>]
 ```
 
 Register in `internal/cli/root.go`:

docs/plans/gitlab-cron-polling-implementation.md

@@ -1492,7 +1492,7 @@ code:
         --event-type "${EVENT_TYPE}" \
         --event-payload-file "${EVENT_PAYLOAD_FILE}" \
         --forge gitlab \
-        --fullsend-dir .fullsend
+        --agent-dir .fullsend
   resource_group: "fullsend-code-${RESOURCE_KEY}"
   rules:
     - if: $STAGE == "code"

docs/plans/universal-harness-access-phase3.md

@@ -56,7 +56,7 @@ harnesses:
 
 ### CLI lock command (`internal/cli/lock.go`)
 
-- `fullsend lock <agent-name> --fullsend-dir <dir>` resolves all deps and writes lock file
+- `fullsend lock <agent-name> --agent-dir <dir>` resolves all deps and writes lock file
 - `--update` flag forces re-resolution even if entry is current
 - Supports `--offline`, `--max-depth`, `--max-resources` flags
 
@@ -78,7 +78,7 @@ harnesses:
 
 ## Verification
 
-1. `fullsend lock code --fullsend-dir .fullsend` generates lock file
+1. `fullsend lock code --agent-dir .fullsend` generates lock file
 2. `fullsend run code` uses lock file when available
 3. Modifying harness triggers stale warning
 4. Missing cache entries produce clear error messages

docs/superpowers/specs/2026-04-17-installer-agent-content-design.md

@@ -271,7 +271,7 @@ Both the `.fullsend` repo and the target repo are checked out side-by-side:
     token: ${{ secrets.FULLSEND_DISPATCH_TOKEN }}
 ```
 
-The composite action then references `--fullsend-dir .fullsend --target-repo target-repo`.
+The composite action then references `--agent-dir .fullsend --target-repo target-repo`.
 
 ---
 

eval/scripts/run-fullsend.sh

@@ -11,7 +11,7 @@
 #   $3 — output directory
 #
 # Required env (injected by harness from hook outputs + execution.env):
-#   FULLSEND_DIR    — path to the fullsend scaffold directory
+#   FULLSEND_DIR    — path to the agent definitions directory
 #   GH_TOKEN        — GitHub token
 #   FIXTURE_URL     — URL of the fixture (issue or PR)
 #   FIXTURE_TYPE    — "issue" or "pull_request"
@@ -68,7 +68,7 @@ mkdir -p "$OUTPUT_DIR"
 
 rc=0
 timeout "$EVAL_TIMEOUT" fullsend run "$AGENT" \
-  --fullsend-dir "${FULLSEND_DIR}" \
+  --agent-dir "${FULLSEND_DIR}" \
   --target-repo "$TARGET_DIR" \
   --env-file "$ENV_FILE" \
   --output-dir "$OUTPUT_DIR" \