agent-exploration

# Agent Exploration Generic parallel-research workflow. Use when a question requires deep reads across multiple distinct areas and the operator needs written artifacts (not chat output). The skill dispatches `explorer` agents in parallel through `compozy exec`; each invocation writes one analysis file. The parent then synthesizes a final summary. The skill is self-contained and harness-agnostic. The explorer is a Compozy agent — a single definition (`assets/AGENT.md`) installed once at `~/.compozy/agents/explorer/AGENT.md`, discoverable by `compozy exec --agent explorer` from any harness (Claude Code, Codex CLI, Cursor, Droid, OpenCode, Pi, Gemini, Copilot, …). The parent runtime is selected per invocation via `--ide`, `--model`, and `--reasoning`. Parallel dispatch uses whatever async/background tool calls your harness exposes — the skill does not prescribe a specific tool. ## Required Reading Router Match your step to the row. Read the listed files **in full before** producing output. They are not appendices — they are load-bearing. Inline content in this SKILL.md is a pointer, not a substitute. | Step | MUST read | | ------------------------------------------------------- | ---------------------------------------------------------------------- | | Step 4 — composing every slice prompt | `references/dispatch-rules.md` + `assets/analysis-template.md` | | Step 5 — verifying outputs | `references/checklist.md` + `assets/analysis-template.md` | | Step 6 — synthesizing `summary.md` | every `<path>/analysis/NN_analysis_<slug>.md` from this round | | Any contract violation, fabricated evidence, or retry | `references/dispatch-rules.md` (re-read; do not paraphrase from memory)| ## Reference Index - `references/dispatch-rules.md` — the scoped-write contract: what the dispatched agent may write, may read, may run; tool allow/forbid lists; parent responsibilities; parallelism cap; failure handling. **Must be embedded verbatim in every slice prompt.** - `references/checklist.md` — seven-section output validation checklist (installation, inputs, scout, dispatch, files, schema, summary). Run before authoring `summary.md`. - `assets/analysis-template.md` — the canonical seven-section schema every dispatched agent fills (Overview, Mechanisms/Patterns, Relevant Sources, Transferable Patterns, Risks/Mismatches, Open Questions, Evidence) plus a Scope header. - `assets/AGENT.md` — the Compozy explorer agent definition (frontmatter: `title`, `description`, `ide`, `model`, `reasoning_effort`, `access_mode`; body: the scoped-write contract and workflow). Installed by `scripts/install-explorer.sh` to `~/.compozy/agents/explorer/AGENT.md`. - `scripts/install-explorer.sh` — bootstrap helper. Writes the bundled `assets/AGENT.md` to the Compozy global registry. Refuses to overwrite. - `scripts/dispatch-slices.sh` — parallel dispatch runner. Takes `--ide`/`--model`/`--reasoning` plus 1-8 prompt files, backgrounds one `compozy exec` per file, waits via `wait $pid`, captures per-slice stdout/stderr/exit, and reports a summary. Zero external dependencies (native bash + the `compozy` binary). ## Bundled Path Rule Resolve every bundled helper relative to the directory that holds this `SKILL.md`. When a command appears below as `scripts/<name>`, treat the actual invocation as `<agent-exploration-dir>/scripts/<name>` — expand `<agent-exploration-dir>` to the absolute skill directory before running. ## Required Inputs - `--path <dir>` (required): Output directory. Analysis files are written under `<path>/analysis/`. Any project-relative or absolute directory works (for example `docs/research/<topic>/`, `tasks/<slug>/`, or a path outside the repo). The skill is not tied to any specific project layout. - `--agents <num>` (optional, default 3, hard cap 8): Number of explorer invocations to dispatch in parallel. - `--prompt <text>` (required): The research question. Quoted multi-line strings are supported. If omitted, the parent asks the operator before continuing. - `--ide <ide>` (optional, default `claude`): Compozy runtime for each dispatched invocation. Forwarded to `compozy exec --ide`. Accepted values mirror `compozy exec`: `codex`, `claude`, `cursor-agent`, `droid`, `opencode`, `pi`, `gemini`, `copilot`. - `--model <name>` (optional, default `opus`): Forwarded to `compozy exec --model`. See **Model Options** for the two supported profiles (Opus default; Grok 4.5 High Fast via `--ide cursor-agent --model 'grok-4.5[effort=high,fast=true]'`). When the chosen IDE does not support the requested model, `compozy` surfaces the error and the slice fails — re-dispatch with a compatible model. - `--reasoning <effort>` (optional, default `xhigh`): Forwarded to `compozy exec --reasoning-effort`. Accepted values: `low`, `medium`, `high`, `xhigh`. If `--path` or `--prompt` is missing, the parent asks the operator a single clarification before continuing. Never invent defaults for either. Apply the documented defaults for `--ide`, `--model`, `--reasoning` silently when omitted; reject an invalid `--ide` rather than falling back. ## Model Options Two dispatch profiles are supported. Opus is the default; Grok 4.5 High Fast is the fast alternative for breadth work. Pick per run via `--ide`/`--model`. | Profile | Flags | When | | -------------------------------------- | -------------------------------------------------------------- | ----------------------------------------------------------- | | Opus (default, high-fidelity) | `--ide claude --model opus --reasoning xhigh` | Hardest slices; when citation precision must be maximal. | | Grok 4.5 High Fast (via cursor-agent) | `--ide cursor-agent --model 'grok-4.5[effort=high,fast=true]'` | Breadth research, cost-sensitive runs, high slice counts. | Grok profile notes: - Reasoning effort and fast mode are pinned inside the model string (`[effort=high,fast=true]`); the `--reasoning` flag does not control this profile. - Single-quote the model string — the square brackets are shell glob characters. ## Output Layout ``` <path>/analysis/ ├── 01_analysis_<slug-a>.md ├── 02_analysis_<slug-b>.md ├── 03_analysis_<slug-c>.md └── summary.md ``` - File numbering is zero-padded to two digits (`01`, `02`, …, `08`). - Each slug is a short kebab-case identifier the parent assigns during the scout (Step 3), reflecting that slice's focus. - `summary.md` is parent-authored synthesis, not a dispatched output. ## Procedures **Step 1: Verify the explorer agent is installed** 1. Confirm the `compozy` binary is on `PATH` (e.g. `command -v compozy`). If missing, abort with a one-line message instructing the operator to install Compozy from `/Users/pedronauck/dev/compozy/looper`. Do not fall back to harness-native subagents. 2. Check for the explorer agent in the Compozy registry: - Global (preferred): `~/.compozy/agents/explorer/AGENT.md`. - Workspace override (optional, takes precedence): `<repo>/.compozy/agents/explorer/AGENT.md`. At least one must be present. 3. If both are absent, ask the operator a single question: "The `explorer` Compozy agent is not installed at `~/.compozy/agents/explorer/AGENT.md`. Install it now? [yes/no]". Do not proceed silently. 4. On "yes", run the bundled bootstrap helper: `<agent-exploration-dir>/scripts/install-explorer.sh`. The helper installs to `~/.compozy/agents/explorer/AGENT.md` and refuses to overwrite an existing file. 5. On "no", abort the dispatch with a one-line message — the agent definition is never inlined into a slice prompt. 6. After installation, re-check that the file exists before continuing. 7. (Optional sanity check) Run `compozy agents inspect explorer` and confirm the entry is discoverable. Any error here blocks dispatch. **Step 2: Resolve inputs** 1. Parse `--path`, `--agents`, `--prompt`, `--ide`, `--model`, `--reasoning` from the invocation. If `--path` or `--prompt` is missing, ask the operator and stop. 2. Default `--agents` to `3` when omitted. Reject values below 1 or above 8 — ask the operator to choose a value in range. 3. Default `--ide` to `claude`, `--model` to `opus`, `--reasoning` to `xhigh` when omitted. Validate `--ide` against the accepted list (`codex`, `claude`, `cursor-agent`, `droid`, `opencode`, `pi`, `gemini`, `copilot`) and `--reasoning` against `low`, `medium`, `high`, `xhigh`; reject invalid values with a clear message instead of silent fallback. Do not validate `--model` ahead of time — let `compozy` surface incompatibilities. 4. Resolve `--path` to an absolute path. If the directory does not exist, ask the operator whether to create it before continuing; if creation fails, stop and report the filesystem error. 5. Create `<path>/analysis/` if absent. The dispatched agents refuse to write into a missing directory. **Step 3: Parent-led initial scout (MANDATORY — do not skip)** The scout is the load-bearing step that prevents wasted parallel dispatch. The parent must do this work itself before any slice is launched. 1. Perform a brief read-only exploration of the problem space using `Glob`, `Grep`, and targeted `Read` calls. The scout's job is to learn enough about the territory to divide it well — not to produce analysis content. Cap the scout at 8–15 tool calls; deep reading belongs to the dispatched agents. 2. From the scout, identify exactly `--agents` distinct slices that are: - **Non-overlapping** — two slices should not require reading the same primary files for the same purpose. - **Independently answerable** — a slice's analysis must not depend on another slice's output. - **Aligned with the operator's `--prompt`** — every slice serves the original research question. 3. For each slice, assign: - A two-digit ordinal (`01`..`08`). - A short kebab-case slug (≤ 4 words) reflecting that slice's focus (e.g. `state-machine`, `event-bus`, `auth-boundaries`). - A focused per-slice prompt that names the slice question, the primary source paths/URLs to read, and any cross-references the dispatched agent should use. 4. Briefly tell the operator the slice list (one line per slice: `NN – slug – focus`) before dispatching. Do not ask for approval unless the slices look thin or overlap; just announce and proceed. If the scout reveals that fewer than `--agents` non-overlapping slices exist, reduce the dispatch count and tell the operator. Do not pad slices to hit the requested count. **Step 4: Dispatch explorer agents in parallel** Gist tripwires — the contract items the parent must enforce in every dispatched prompt: - The prompt names three things: slice scope, slug+ordinal, exact target file path. If any is missing, the dispatched agent must refuse and ask back. - The dispatched agent gets exactly one file-write — at the named target path — and nothing else. No edits, no `git`/`make`/package managers, no writes outside `<path>/analysis/`. - All slices dispatch in parallel via `compozy exec`, with `--ide`/`--model`/`--reasoning-effort` forwarded from the operator's inputs. Wait for every process to exit (code 0) before verification. **STOP. Read `references/dispatch-rules.md` in full before composing any slice prompt.** That file contains the complete scoped-write contract, tool allow/forbid lists, parent responsibilities, and failure handling. The bullets above are tripwires, not the contract — the contract must be embedded verbatim in every slice prompt. **STOP. Read `assets/analysis-template.md` in full before composing any slice prompt.** That file is the canonical seven-section schema every dispatched agent fills. The schema must be embedded in the prompt; do not paraphrase it. Compose one slice prompt per slice. Every prompt MUST include: - The operator's original `--prompt` verbatim, prefixed by a short orientation line. - The slice's focused question and the primary sources to read. - The exact target path: `<path>/analysis/NN_analysis_<slug>.md` (absolute path). - `references/dispatch-rules.md` content embedded verbatim (copy-paste, do not paraphrase). - The seven-section schema from `assets/analysis-template.md`. Write each composed prompt to its own file at `<path>/.dispatch/prompts/NN_<slug>.txt`. The file basename (without extension) becomes the slice id used for per-slice log file naming. **Recommended dispatch path: `scripts/dispatch-slices.sh`.** The bundled script backgrounds one `compozy exec` per prompt file, waits for every PID, captures per-slice stdout/stderr/exit under `<logs-dir>`, and exits non-zero if any slice failed. Zero external dependencies; portable across any harness that can run a bash script. ``` <agent-exploration-dir>/scripts/dispatch-slices.sh \ --ide <ide> --model <model> --reasoning <reasoning> \ --logs <path>/.dispatch/logs \ -- <path>/.dispatch/prompts/01_<slug-a>.txt \ <path>/.dispatch/prompts/02_<slug-b>.txt \ <path>/.dispatch/prompts/03_<slug-c>.txt ``` - `<ide>`, `<model>`, `<reasoning>` are the resolved operator inputs (defaults `claude`, `opus`, `xhigh`). - The script prints `dispatched: <slug> pid=<N>` per launch and `exited: <slug> rc=<N>` per completion, ending with a `summary: total=Xs ok=N/M failed=K/M` line. - Each prompt is passed through `compozy exec --prompt-file <file>` (no shell-escaping risk for long prompts). - The script hard-caps at 8 slices per invocation, matching the parallelism cap in `references/dispatch-rules.md`. **Manual alternative** (if you cannot run a bash script — e.g., a harness that prefers issuing N parallel tool calls itself): invoke each slice with the command shape below. Use whatever async/background facility your harness exposes; wait for every invocation to exit before continuing. ``` compozy exec \ --agent explorer \ --ide <ide> \ --model <model> \ --reasoning-effort <reasoning> \ --prompt-file <path>/.dispatch/prompts/NN_<slug>.txt ``` Notes that apply to both paths: - `compozy exec` already defaults `--access-mode` to `full`, so no extra runtime-permission flag is required. - **When `--ide cursor-agent` (Grok profile), reasoning effort is pinned in the model string** (`grok-4.5[effort=high,fast=true]`); the forwarded `--reasoning-effort` value does not control it (see Model Options).