manage
The manage-level front door to ACED — the user-facing handler for non-mission work on the
agent-config tooling corpus. Where define-agent / define-skill author a config and run /
add-scenario score one, manage does the work that is neither: inspect and maintain the
tooling ACED evaluates.
manage is a thin dispatcher: it classifies a manage request and loads the matching engine in
the current session, holding no production logic, loading no governance, and writing no
contract state. It opens no CR, invokes no gate, and performs no behavior change itself.
Manage picks no model. The model + effort a piece of work needs is set by the engine you
load. The loaded engine advises; the user switches manually. (manage cannot switch the session
model itself.)
Intake
- Fast path — skip the menu. When the invocation already names the operation — "set up the
model runners", "list the runners", "remove the haiku runner" — load the matching engine directly,
no menu.
- Menu — bare invocation. When
manage is invoked with no operation named, do not guess. Ask
via AskUserQuestion, presenting at most four options (the tool rejects more than four) and
never truncating silently. The route groups today (Config runners, Skill corpus) fit the
four-option rule; as more manage-level engines land, group the menu so a bare invocation still
resolves within it.
The routing table — request → engine
Classification routes a manage request to the engine that handles it. The table grows as more
manage-level ACED engines land:
| Group |
Request |
Engine (handler) |
| Config runners |
set up / list / remove per-model runner agents used to benchmark skills |
manage-model-runners — internal, non-invokable; loaded here |
| Skill corpus |
list / inventory the installed skills across the repo, the user-global install, and the shipped package |
list-skills — internal, non-invokable; loaded here |
| Skill corpus |
validate / repair repo-private skill metadata under .agents/skills |
repair-private-skills — internal, non-invokable; loaded here |
| Skill corpus |
list / add / remove / preview the extra skill-scan locations the validate engine uses |
manage-skill-dirs — internal, non-invokable; loaded here |
Load the engine in-session
When the route resolves, load the matched engine in the current session and run it directly —
spawn nothing. Write-capable operations stay owned by their engine: manage-model-runners
writes its runner agent-def files and their symlinks; repair-private-skills writes only under
.agents/skills; manage-skill-dirs writes only .agents/aced/skill-dirs.toml; list-skills is
read-only. manage only routes.
Non-mission — the boundary
manage maintains and inspects the ACED tooling corpus; it never changes what ACED specifies.
- Opens no CR, invokes no gate, writes no
status / approval. Those belong to start-mission
and the internal gates.
- Authoring is not manage. A request to create or improve an agent definition or a workflow
skill is redirected to
define-agent / define-skill, not handled here.
- Scoring is not manage. A request to run or score a config's eval suite defers to the
eval-run skills (
run / compare / report).
- A change to what ACED specifies — adding or revising ACED's own behavior — is redirected to
start-mission, which opens a CR and runs the mission loop.
- Thin classifier. Classifying loads no governance and holds no production logic — it
only loads the matched engine.
1---2name: manage-23description: Use this skill when doing manage-level (non-mission) ACED work — inspecting or maintaining the agent-config tooling ACED evaluates, such as "set up the per-model runner agents", "list the model runners", "list the installed skills", or "validate/repair the repo-private skills". Routes to the matching engine; it does not author a config (define-agent / define-skill) or change what ACED specifies (start-mission).4---56# manage78The **manage-level** front door to ACED — the user-facing handler for **non-mission** work on the9agent-config tooling corpus. Where `define-agent` / `define-skill` **author** a config and `run` /10`add-scenario` **score** one, `manage` does the work that is neither: **inspect and maintain** the11tooling ACED evaluates.1213`manage` is a **thin dispatcher**: it classifies a manage request and **loads the matching engine in14the current session**, holding **no production logic**, loading **no governance**, and writing **no15contract state**. It **opens no CR**, **invokes no gate**, and **performs no behavior change** itself.1617> **Manage picks no model.** The model + effort a piece of work needs is set by the **engine you18> load**. The loaded engine advises; the user switches manually. (`manage` cannot switch the session19> model itself.)2021## Intake2223- **Fast path — skip the menu.** When the invocation already **names the operation** — "set up the24 model runners", "list the runners", "remove the haiku runner" — load the matching engine directly,25 no menu.26- **Menu — bare invocation.** When `manage` is invoked with **no operation named**, do not guess. Ask27 via `AskUserQuestion`, presenting **at most four options** (the tool rejects more than four) and28 never truncating silently. The route groups today (**Config runners**, **Skill corpus**) fit the29 four-option rule; as more manage-level engines land, group the menu so a bare invocation still30 resolves within it.3132## The routing table — request → engine3334Classification routes a manage request to the **engine** that handles it. The table grows as more35manage-level ACED engines land:3637| Group | Request | Engine (handler) |38|---|---|---|39| **Config runners** | set up / list / remove per-model runner agents used to benchmark skills | **`manage-model-runners`** — internal, non-invokable; loaded here |40| **Skill corpus** | list / inventory the installed skills across the repo, the user-global install, and the shipped package | **`list-skills`** — internal, non-invokable; loaded here |41| **Skill corpus** | validate / repair repo-private skill metadata under `.agents/skills` | **`repair-private-skills`** — internal, non-invokable; loaded here |42| **Skill corpus** | list / add / remove / preview the extra skill-scan locations the validate engine uses | **`manage-skill-dirs`** — internal, non-invokable; loaded here |4344## Load the engine in-session4546When the route resolves, **load the matched engine in the current session** and run it directly —47**spawn nothing**. Write-capable operations stay **owned by their engine**: `manage-model-runners`48writes its runner agent-def files and their symlinks; `repair-private-skills` writes only under49`.agents/skills`; `manage-skill-dirs` writes only `.agents/aced/skill-dirs.toml`; `list-skills` is50read-only. `manage` only routes.5152## Non-mission — the boundary5354`manage` maintains and inspects the ACED tooling corpus; it **never changes what ACED specifies**.5556- **Opens no CR, invokes no gate, writes no `status` / `approval`.** Those belong to `start-mission`57 and the internal gates.58- **Authoring is not manage.** A request to **create or improve** an agent definition or a workflow59 skill is redirected to **`define-agent`** / **`define-skill`**, not handled here.60- **Scoring is not manage.** A request to **run or score** a config's eval suite defers to the61 **eval-run** skills (`run` / `compare` / `report`).62- **A change to what ACED specifies** — adding or revising ACED's own behavior — is redirected to63 **`start-mission`**, which opens a CR and runs the mission loop.64- **Thin classifier.** Classifying loads **no governance** and holds **no production logic** — it65 only loads the matched engine.
cyberuni