@jaybeeuu/agent-cortex 1.20.0 → 1.38.1

package/token-map.README.md

@@ -0,0 +1,128 @@
+# token-map.json — multi-harness token substitution
+
+`token-map.json` is the central, single-source mapping of **tool names**, **paths**, and
+**agent naming conventions** across the three harnesses this repo ships to. It is the
+foundation for the install-time generation system: each harness installer (`agent-cortex
+install <harness>`) reads the map and substitutes `{{TOOL:...}}` / `{{PATH:...}}` tokens in
+the files it generates.
+
+**The substitution contract lives inside `token-map.json`** (the `contract` section) — that
+file is the single reference installers must implement. This README explains the design
+decisions behind the map.
+
+## Harnesses
+
+| id | Platform | Agent format | Plugin root |
+|---|---|---|---|
+| `copilot` | GitHub Copilot CLI | `agents/<name>/` composable dirs → generated `agents/*.agent.md` | `~/.copilot/installed-plugins/_direct/agent-cortex` |
+| `pi` | pi coding agent | `agents/<name>/` composable dirs (composed at runtime by agent-modes, or installed install-time by `agent-cortex install pi`) | `~/.pi/agent/npm/node_modules/@jaybeeuu/agent-cortex` |
+| `claude` | Claude Code | `claude/agents/*.md` (generated) | `${CLAUDE_PLUGIN_ROOT}` (env var) |
+
+The harness ids match the values accepted by `agent-cortex install <harness>` in
+`lib/cli.mjs` (`SUPPORTED_HARNESSES`). The pi `plugin_root` row is the npm-layout
+literal that `agent-cortex install pi` uses by default; local checkout and symlinked
+installs pass `--plugin-root <dir>` to override it (see README "Pi harness agents &
+skills").
+
+## Design decisions
+
+### 1. Token naming convention: `{{TOOL:name}}`, not `{{tool.name}}`
+
+`agents/README.md` (ADR #63) already standardised `{{TOOL:name}}`, `{{PATH:name}}`, and
+`{{SECTION:name}}` for the composable agent directory format. The map adopts that grammar
+rather than inventing a dotted form:
+
+- **The convention is established** — skill authors and the ADR already write tokens this
+  way; the map should not fork the language.
+- **Upper-case type prefix disambiguates** — `{{TOOL:read}}` (a tool) can never collide with
+  `{{PATH:read}}` (a path) in the same document.
+- **One namespace per type** — tool keys, path keys, and section names never share a lookup
+  table, so a tool called `skills_dir` would not shadow the path key.
+- **Greppable and schema-friendly** — simple `{{TYPE:NAME}}` is trivially matched by a
+  regex; delimiters make unbalanced/typo'd tokens visible.
+
+### 2. What is mapped
+
+- **`tools`** — the twelve canonical tool names as authored in `agents/<name>/agent.md`
+  (copilot names are the authoring names). Each row gives the equivalent tool name per
+  harness. Source of truth for the copilot → claude half is `token-map.json`'s own claude
+  column, consumed by `bin/installers/claude.mjs` (the install-time generator — PR #91, #92); the pi column is grounded
+  in pi's documented built-in tool surface (`read`, `bash`, `edit`, `write`, `grep`, `find`,
+  `ls`) plus `task` / `read_agent` / `wait_for_agents` subagent tools.
+- **`paths`** — `plugin_root`, `agents_dir`, and `skills_dir`. These are the install-time
+  variables that differ per harness. `plugin_root` is the anchor; the other two resolve
+  relative to it (`{base, relative}` specs) so a harness only overrides the single root it
+  actually installs into.
+- **`agents`** — the `agent-cortex:` name-prefix convention per harness (claude strips the
+  prefix during conversion) and the deferred-agent exception (claude's `ralph` is authored
+  natively, never generated). Agent names themselves do not get per-row mappings because
+  the prefix rule covers all of them; the deferred list captures the only structural
+  difference.
+- **Deliberately not mapped:** hook patterns, MCP servers, and tool descriptions. Those
+  differ *structurally* per harness (different hook event names, different config files),
+  not by a single substitutable token; each installer already hardcodes its own shape. The
+  map records them in `notes` where a tool differs in behaviour (`read_agent`, `skill`,
+  `ask_user`).
+
+### 3. Null mappings
+
+A null value means **"this harness has no equivalent"** — not "empty string" and not "leave
+the token as-is". The contract defines the two contexts:
+
+- **Prose** (e.g. `Use {{TOOL:read_agent}} to poll`): the token is dropped and the
+  installer warns. Dangling sentences after a drop are the author's responsibility — the
+  warning exists so the installer surfaces them.
+- **Tool-list frontmatter** (e.g. `tools: [..., "read_agent"]`): the entry is omitted from
+  the array.
+
+Unknown (unmapped) tokens are a **hard error**, not a null — a silently-passed-through
+token is exactly the bug the map exists to prevent, and mirrors the build script's
+`unknown tool "x"` throw.
+
+The pi install-time installer (`bin/installers/pi.mjs`) follows the strict contract above.
+One consumer deviates deliberately: the pi `agent-modes` extension reads the map at
+**runtime** (not install time) to compose agent prompts from the composable agents
+format. For it, an unmapped tool name passes through unchanged — it may be a
+native PI tool — while a mapped-null tool (`ask_user`, `skill`) is omitted with a
+warning. See `extensions/agent-modes/README.md`.
+
+### 4. Token substitution contract
+
+The full contract is embedded in `token-map.json` under `contract`. In summary, installers:
+
+1. Bind a harness id (`copilot` | `claude` | `pi`).
+2. Substitute in order: `SECTION` (left for the composer), then `TOOL`, then `PATH`.
+3. For `TOOL`: look up the canonical key, replace with the harness name; null → drop/omit;
+   unknown → throw.
+4. For `PATH`: named key → resolve from `paths`; anything else → resolve relative to
+   `plugin_root`; `${ENV_VAR}` values pass through verbatim for runtime expansion.
+5. Reject a map `version` they do not implement.
+
+## Authoring guidance
+
+- Write tokens with the **canonical (copilot) names**: `Use {{TOOL:task}} to spawn
+  subagents`, `Read {{PATH:skills/workflow/plan/SKILL.md}}`.
+- Never embed a harness-specific name in the canonical sources (`agents/<name>/agent.md`,
+  `skills/**/SKILL.md`) — that defeats the map. The generated `claude/` subtree, the
+  generated `agents/*.agent.md` files, and any installed copies are the only places
+  substituted names appear.
+- When you add a new tool to an agent's frontmatter, add a row to `tools` in
+  `token-map.json` in the same change — the contract treats unknown tools as errors, so a
+  missing row breaks the install pipeline loudly instead of silently.
+
+## Related
+
+- `agents/README.md` — composable agent directory format (ADR #63), defines the token
+  grammar the map implements.
+- `scripts/build-copilot-agents.mjs` / `bin/installers/copilot.mjs` — the copilot
+  harness token composer (scripts/lib/compose-agent.mjs) resolves `{{TOOL:...}}` /
+  `{{PATH:...}}` against the map and `{{SECTION:...}}` from the per-harness section
+  files; `bin/installers/copilot.mjs` is the shared generator both `pnpm build:copilot`
+  and `agent-cortex install copilot` run.
+- `bin/installers/claude.mjs` — the single Claude generator, behind both
+  `agent-cortex install claude` and the `pnpm build:claude` alias (no build-time
+  counterpart; the committed `claude/` subtree is regenerated by it and drift-checked).
+- `bin/installers/pi.mjs` — the pi harness installer (`agent-cortex install pi`), an
+  install-time consumer of the map's contract.
+- `lib/cli.mjs` — `SUPPORTED_HARNESSES`, the install command surface the harness ids come
+  from.

package/token-map.json

@@ -0,0 +1,106 @@
+{
+  "name": "agent-cortex token map",
+  "description": "Central mapping of tool names, paths, and agent naming conventions across the copilot, claude, and pi harnesses. Single source of truth for install-time token substitution. See token-map.README.md for the design rationale.",
+  "version": 1,
+  "harnesses": ["copilot", "claude", "pi"],
+  "token_format": {
+    "convention": "{{TYPE:NAME}}",
+    "decision": "Adopt the {{TOOL:name}} / {{PATH:name}} / {{SECTION:name}} grammar already standardised by ADR #63 (agents/README.md) rather than a dotted {{tool.name}} form. The uppercase type prefix disambiguates token kinds at a glance, keeps tool/path/section names in one namespace collision-free, and matches the token grammar skills are already written against.",
+    "types": {
+      "TOOL": "{{TOOL:<canonical tool key>}} — replaced at install time with the bound harness's tool name (see tools).",
+      "PATH": "{{PATH:<path key or relative path>}} — replaced at install time with the harness-resolved path (see paths).",
+      "SECTION": "{{SECTION:<name>}} — replaced by the agent composer with <harness>/<name>.md section content. Not a global substitution; out of scope for token-map.json (see contract)."
+    }
+  },
+  "tools": {
+    "bash": { "copilot": "bash", "claude": "Bash", "pi": "bash" },
+    "view": { "copilot": "view", "claude": "Read", "pi": "read" },
+    "edit": { "copilot": "edit", "claude": "Edit", "pi": "edit" },
+    "create": { "copilot": "create", "claude": "Write", "pi": "write" },
+    "grep": { "copilot": "grep", "claude": "Grep", "pi": "grep" },
+    "rg": { "copilot": "rg", "claude": "Grep", "pi": "grep" },
+    "glob": { "copilot": "glob", "claude": "Glob", "pi": "find" },
+    "ask_user": { "copilot": "ask_user", "claude": "AskUserQuestion", "pi": null },
+    "web_fetch": { "copilot": "web_fetch", "claude": "WebFetch", "pi": "fetch_content" },
+    "skill": { "copilot": "skill", "claude": "Skill", "pi": null },
+    "task": { "copilot": "task", "claude": "Task", "pi": "task" },
+    "read_agent": { "copilot": "read_agent", "claude": null, "pi": "read_agent" },
+    "wait_for_agents": { "copilot": null, "claude": null, "pi": "wait_for_agents" }
+  },
+  "paths": {
+    "plugin_root": {
+      "copilot": "~/.copilot/installed-plugins/_direct/agent-cortex",
+      "claude": "${CLAUDE_PLUGIN_ROOT}",
+      "pi": "~/.pi/agent/npm/node_modules/@jaybeeuu/agent-cortex"
+    },
+    "agents_dir": {
+      "copilot": { "base": "plugin_root", "relative": "agents" },
+      "claude": { "base": "plugin_root", "relative": "agents" },
+      "pi": { "base": "plugin_root", "relative": "agents" }
+    },
+    "skills_dir": {
+      "copilot": { "base": "plugin_root", "relative": "skills" },
+      "claude": { "base": "plugin_root", "relative": "skills" },
+      "pi": { "base": "plugin_root", "relative": "skills" }
+    }
+  },
+  "agents": {
+    "prefix": {
+      "copilot": "agent-cortex:",
+      "claude": "",
+      "pi": "agent-cortex:"
+    },
+    "deferred": {
+      "ralph": ["claude"]
+    },
+    "sources": {
+      "copilot": "agents/<name>/ composable dirs (canonical) — composed to agents/*.agent.md by scripts/build-copilot-agents.mjs",
+      "pi": "agents/<name>/ composable dirs (canonical) — composed at runtime by the agent-modes extension",
+      "claude": "agents/<name>/ composable dirs (canonical) — composed by bin/installers/claude.mjs (install-time generator; pnpm build:claude aliases it), plus agents-native/*.md for deferred agents"
+    }
+  },
+  "notes": {
+    "tools": {
+      "rg": "Copilot alias for grep. Claude and pi collapse it onto their single search tool (Grep / grep) — same collapse rule as the build script.",
+      "glob": "Claude has a dedicated Glob tool. pi's built-in pattern-search tool is find (hypa_find when the pi-hypa extension is installed).",
+      "ask_user": "Copilot (ask_user) and Claude (AskUserQuestion) prompt the user mid-run. pi intentionally ships no permission-popup/ask tool (per pi docs 'it intentionally does not include permission popups'), so the mapping is null.",
+      "web_fetch": "pi's fetch_content comes from the pi-web-access package (declared in pi/settings.json).",
+      "skill": "Copilot (skill) and Claude (Skill) expose skills as a tool. pi discovers skills but the agent loads them via read and /skill:<name> commands — there is no dedicated tool, so the mapping is null.",
+      "read_agent": "Claude's Task returns results inline — there is no separate read step, so read_agent drops on claude (null). Copilot uses the task + read_agent poll loop; pi blocks on wait_for_agents and keeps read_agent as a fallback.",
+      "wait_for_agents": "PI-only blocking wait over background subagent runs (the task tool): returns the results of completed agents and STILL RUNNING for the rest. Copilot has no equivalent tool (its task + read_agent poll loop stays) and Claude's Task delivers results inline with no wait step — both null."
+    },
+    "paths": {
+      "pi": "plugin_root defaults to the npm-package install layout (~/.pi/agent/npm/node_modules/@jaybeeuu/agent-cortex). Local-checkout installs (pi/settings.json packages entry referencing a local src path) or symlinked installs differ — installers must compute plugin_root from the actual resolution and can override it."
+    },
+    "agents": {
+      "prefix": "Claude strips the agent-cortex: name prefix during conversion (NAME_PREFIX in bin/installers/claude.mjs): copilot/pi agents are agent-cortex:<slug>, claude agents are <slug>.",
+      "deferred": "ralph has no generated claude counterpart — it is authored natively as agents-native/ralph.md (its event-driven orchestration cannot be produced by section composition from the polling copilot source)."
+    }
+  },
+  "contract": {
+    "version": 1,
+    "summary": "Installers substitute {{TOOL:...}}, {{PATH:...}}, and {{SECTION:...}} tokens in generated harness files using this map. This contract is the single reference installers must implement; token-map.json is the data those rules operate on.",
+    "harness_ids": ["copilot", "claude", "pi"],
+    "binding": "The harness id is the same value the installer is invoked with (agent-cortex install <harness>). Each harness reads its own column from the tools, paths, and agents sections.",
+    "substitution_order": ["SECTION", "TOOL", "PATH"],
+    "rules": [
+      "TOOL: replace {{TOOL:<key>}} with tools.<key>.<harness>. Canonical keys are exact, case-sensitive strings (the copilot tool names, which are the authoring names in agents/<name>/agent.md).",
+      "TOOL null: a null value means the harness has no equivalent. In prose, remove the token (and emit a warning). In a tool-list context (frontmatter tools: [...]), omit the entry. Do not substitute an empty string.",
+      "TOOL unknown: a {{TOOL:<key>}} with no entry in tools is a hard error — the map must be extended. This mirrors the generators (scripts/build-copilot-agents.mjs, bin/installers/claude.mjs), which throw on unknown tools.",
+      "PATH named key: replace {{PATH:<key>}} with the resolved value of paths.<key>.<harness>.",
+      "PATH relative: replace {{PATH:<relative>}} with plugin_root + '/' + <relative> (e.g. {{PATH:skills/workflow/plan/SKILL.md}}).",
+      "PATH resolution: a value may be a literal string, an ${ENV_VAR} token, or a {base, relative} spec. Resolve {base, relative} by joining relative onto the resolved base. Leave ${ENV_VAR} values verbatim — the harness expands them at runtime (claude's ${CLAUDE_PLUGIN_ROOT}).",
+      "PATH unknown base: a {base, relative} spec whose base is not a key in paths is a hard error.",
+      "SECTION: {{SECTION:<name>}} is resolved by the agent composer from <agents_dir>/<harness>/<name>.md; token-map.json does not substitute it. Installers must leave SECTION tokens untouched for the composer.",
+      "Contract version: installers must reject token-map.json versions higher than the contract version they implement.",
+      "Case sensitivity: all token arguments and map keys are case-sensitive."
+    ],
+    "error_handling": {
+      "unknown_tool": "throw — the map must stay complete",
+      "unknown_path_base": "throw — the map must stay complete",
+      "null_tool_in_prose": "warn and drop the token",
+      "null_tool_in_tool_list": "omit the entry from the array",
+      "unsupported_version": "throw with the supported version range"
+    }
+  }
+}

package/.beads/README.md

@@ -1,81 +0,0 @@
-# Beads - AI-Native Issue Tracking
-
-Welcome to Beads! This repository uses **Beads** for issue tracking - a modern, AI-native tool designed to live directly in your codebase alongside your code.
-
-## What is Beads?
-
-Beads is issue tracking that lives in your repo, making it perfect for AI coding agents and developers who want their issues close to their code. No web UI required - everything works through the CLI and integrates seamlessly with git.
-
-**Learn more:** [github.com/steveyegge/beads](https://github.com/steveyegge/beads)
-
-## Quick Start
-
-### Essential Commands
-
-```bash
-# Create new issues
-bd create "Add user authentication"
-
-# View all issues
-bd list
-
-# View issue details
-bd show <issue-id>
-
-# Update issue status
-bd update <issue-id> --claim
-bd update <issue-id> --status done
-
-# Sync with Dolt remote
-bd dolt push
-```
-
-### Working with Issues
-
-Issues in Beads are:
-- **Git-native**: Stored in Dolt database with version control and branching
-- **AI-friendly**: CLI-first design works perfectly with AI coding agents
-- **Branch-aware**: Issues can follow your branch workflow
-- **Always in sync**: Auto-syncs with your commits
-
-## Why Beads?
-
-✨ **AI-Native Design**
-- Built specifically for AI-assisted development workflows
-- CLI-first interface works seamlessly with AI coding agents
-- No context switching to web UIs
-
-🚀 **Developer Focused**
-- Issues live in your repo, right next to your code
-- Works offline, syncs when you push
-- Fast, lightweight, and stays out of your way
-
-🔧 **Git Integration**
-- Automatic sync with git commits
-- Branch-aware issue tracking
-- Dolt-native three-way merge resolution
-
-## Get Started with Beads
-
-Try Beads in your own projects:
-
-```bash
-# Install Beads
-curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash
-
-# Initialize in your repo
-bd init
-
-# Create your first issue
-bd create "Try out Beads"
-```
-
-## Learn More
-
-- **Documentation**: [github.com/steveyegge/beads/docs](https://github.com/steveyegge/beads/tree/main/docs)
-- **Quick Start Guide**: Run `bd quickstart`
-- **Examples**: [github.com/steveyegge/beads/examples](https://github.com/steveyegge/beads/tree/main/examples)
-
----
-
-*Beads: Issue tracking that moves at the speed of thought* ⚡

package/.beads/config.yaml

@@ -1 +0,0 @@
-no-git-ops: true