cohorte 2.10.1 → 3.0.0-dev.1

package/core/runtimes/codex.json

@@ -1,85 +0,0 @@
-{
-  "id": "codex",
-  "label": "Codex CLI (OpenAI)",
-  "docs": "https://learn.chatgpt.com/docs/build-skills",
-  "detect": [
-    "~/.codex"
-  ],
-  "notes": [
-    "Commands ship as SKILLS (.agents/skills/<name>/SKILL.md), not as custom prompts. Prompts are",
-    "deprecated, and they are user-scoped only (~/.codex/prompts) \u2014 so a teammate cloning the repo",
-    "would get the profile but none of the commands. Skills are discovered from `.agents/skills` in",
-    "the repo, which means they travel with it. Invoked as $<name>, or implicitly from `description`.",
-    "Skills do NOT substitute arguments, so the preamble explains $ARGUMENTS rather than rewriting it.",
-    "Subagents are TOML, one file per agent, and the body lives in `developer_instructions`.",
-    "Hooks use the SAME PreToolUse envelope as Claude Code, with one difference that matters:",
-    "`permissionDecision: ask` is parsed but not honoured, so gate.py escalates ask to deny here.",
-    "Anthropic model aliases are dropped and default to inheritance. Explicit Codex model and model_reasoning_effort values are preserved. Surface agents always live in the current project's .codex/agents, even with a global core; CODEX_HOME does not change."
-  ],
-  "scopes": {
-    "global": {
-      "root": "~/.codex",
-      "core": "~/.cohorte/codex",
-      "commands": "~/.agents/skills",
-      "agents": "~/.codex/agents",
-      "hooks": "~/.cohorte/codex/hooks",
-      "hooks_config": "~/.codex/hooks.json",
-      "workflows": null,
-      "settings": null
-    },
-    "project": {
-      "root": ".codex",
-      "core": ".cohorte/codex",
-      "commands": ".agents/skills",
-      "agents": ".codex/agents",
-      "hooks": ".cohorte/codex/hooks",
-      "hooks_config": ".codex/hooks.json",
-      "workflows": null,
-      "settings": null
-    }
-  },
-  "exclude_commands": [],
-  "command": {
-    "format": "skill",
-    "ext": "/SKILL.md",
-    "frontmatter": [
-      "name",
-      "description"
-    ],
-    "args": null,
-    "args_note": "the text you typed after the skill name",
-    "invoke": "$<name>"
-  },
-  "agent": {
-    "format": "toml",
-    "ext": ".toml",
-    "body_key": "developer_instructions",
-    "frontmatter": [
-      "name",
-      "description",
-      "model",
-      "model_reasoning_effort"
-    ],
-    "readonly_key": "sandbox_mode",
-    "readonly_value": "read-only",
-    "dispatch": "spawn the named agent; several run in parallel and Codex returns a consolidated result",
-    "address": "<name>"
-  },
-  "hook": {
-    "format": "claude",
-    "event": "PreToolUse",
-    "matcher": "Bash|shell|spawn_agent|Agent",
-    "supports_ask": false,
-    "config_shape": "json"
-  },
-  "capabilities": {
-    "subagents": true,
-    "hooks": true,
-    "workflows": false,
-    "inline_design": false,
-    "mcp": true,
-    "tool_restriction": true
-  },
-  "memory": "AGENTS.md",
-  "headless": "codex exec"
-}

package/core/runtimes/cursor.json

@@ -1,76 +0,0 @@
-{
-  "id": "cursor",
-  "label": "Cursor",
-  "docs": "https://cursor.com/docs/cli/overview",
-  "detect": [
-    "~/.cursor"
-  ],
-  "notes": [
-    "Cursor commands are plain markdown with NO placeholder substitution: whatever the human",
-    "types after the command name is appended to the prompt. The adapter therefore explains the",
-    "argument placeholder in the preamble rather than rewriting it to a token.",
-    "Subagents are markdown + frontmatter, and `readonly: true` is a real tool restriction \u2014",
-    "the review agent gets it. Cursor also reads .claude/agents and .codex/agents.",
-    "Hooks use Cursor's own envelope ({\"permission\": \u2026}), not Claude's.",
-    "Model pins are NOT carried across: the profile names Anthropic aliases (sonnet/haiku), which are meaningless here and would either error or be silently ignored. Agents and commands inherit this runtime's own model selection instead."
-  ],
-  "scopes": {
-    "global": {
-      "root": "~/.cursor",
-      "core": "~/.cohorte/cursor",
-      "commands": "~/.cursor/commands",
-      "agents": "~/.cursor/agents",
-      "hooks": "~/.cohorte/cursor/hooks",
-      "hooks_config": "~/.cursor/hooks.json",
-      "workflows": null,
-      "settings": null
-    },
-    "project": {
-      "root": ".cursor",
-      "core": ".cohorte/cursor",
-      "commands": ".cursor/commands",
-      "agents": ".cursor/agents",
-      "hooks": ".cohorte/cursor/hooks",
-      "hooks_config": ".cursor/hooks.json",
-      "workflows": null,
-      "settings": null
-    }
-  },
-  "exclude_commands": [],
-  "command": {
-    "format": "md",
-    "ext": ".md",
-    "frontmatter": [],
-    "args": null,
-    "args_note": "the text you typed after the command name",
-    "invoke": "/<name>"
-  },
-  "agent": {
-    "format": "md",
-    "ext": ".md",
-    "frontmatter": [
-      "name",
-      "description"
-    ],
-    "readonly_key": "readonly",
-    "readonly_value": "true",
-    "dispatch": "invoke it as /<name> <brief>, or name it in the prompt; several run in parallel",
-    "address": "/<name>"
-  },
-  "hook": {
-    "format": "cursor",
-    "event": "beforeShellExecution",
-    "supports_ask": true,
-    "config_shape": "json"
-  },
-  "capabilities": {
-    "subagents": true,
-    "hooks": true,
-    "workflows": false,
-    "inline_design": false,
-    "mcp": true,
-    "tool_restriction": true
-  },
-  "memory": "AGENTS.md",
-  "headless": "cursor-agent -p"
-}

package/core/runtimes/gemini.json

@@ -1,76 +0,0 @@
-{
-  "id": "gemini",
-  "label": "Gemini CLI",
-  "docs": "https://geminicli.com/docs/",
-  "detect": [
-    "~/.gemini"
-  ],
-  "notes": [
-    "Commands are TOML, not markdown: the whole prompt body becomes the `prompt` key, and the",
-    "argument placeholder is {{args}}. Sub-directories namespace with ':'.",
-    "Subagents ARE markdown + frontmatter (.gemini/agents), and are exposed to the main agent as",
-    "a tool of the same name; @agent-name forces one. They cannot call other subagents.",
-    "Hooks live in settings.json under `hooks`, event `BeforeTool`, matched on the tool name",
-    "(run_shell_command). The envelope is {\"decision\": \"deny\", \"reason\": \u2026} with no ask tier.",
-    "Model pins are NOT carried across: the profile names Anthropic aliases (sonnet/haiku), which are meaningless here and would either error or be silently ignored. Agents and commands inherit this runtime's own model selection instead."
-  ],
-  "scopes": {
-    "global": {
-      "root": "~/.gemini",
-      "core": "~/.cohorte/gemini",
-      "commands": "~/.gemini/commands",
-      "agents": "~/.gemini/agents",
-      "hooks": "~/.cohorte/gemini/hooks",
-      "hooks_config": "~/.gemini/settings.json",
-      "workflows": null,
-      "settings": "~/.gemini/settings.json"
-    },
-    "project": {
-      "root": ".gemini",
-      "core": ".cohorte/gemini",
-      "commands": ".gemini/commands",
-      "agents": ".gemini/agents",
-      "hooks": ".cohorte/gemini/hooks",
-      "hooks_config": ".gemini/settings.json",
-      "workflows": null,
-      "settings": ".gemini/settings.json"
-    }
-  },
-  "exclude_commands": [],
-  "command": {
-    "format": "toml",
-    "ext": ".toml",
-    "frontmatter": [
-      "description"
-    ],
-    "args": "{{args}}",
-    "invoke": "/<name>"
-  },
-  "agent": {
-    "format": "md",
-    "ext": ".md",
-    "frontmatter": [
-      "name",
-      "description"
-    ],
-    "dispatch": "the subagent is exposed as a tool of the same name; @<name> forces it",
-    "address": "@<name>"
-  },
-  "hook": {
-    "format": "gemini",
-    "event": "BeforeTool",
-    "matcher": "run_shell_command",
-    "supports_ask": false,
-    "config_shape": "settings"
-  },
-  "capabilities": {
-    "subagents": true,
-    "hooks": true,
-    "workflows": false,
-    "inline_design": false,
-    "mcp": true,
-    "tool_restriction": false
-  },
-  "memory": "GEMINI.md",
-  "headless": "gemini -p"
-}

package/core/runtimes/opencode.json

@@ -1,73 +0,0 @@
-{
-  "id": "opencode",
-  "label": "OpenCode",
-  "docs": "https://opencode.ai/docs/cli/",
-  "detect": [
-    "~/.config/opencode",
-    "~/.opencode"
-  ],
-  "notes": [
-    "Markdown agents in agents/ with `mode: subagent`, addressed with @<name>.",
-    "The one runtime here with NO hook mechanism \u2014 extension is via plugins (.opencode/plugin/*.js),",
-    "which is a different contract from a blocking PreToolUse hook. The gate therefore runs in",
-    "explicit --check mode, which is advisory by construction.",
-    "`opencode run` is the headless primitive; --agent selects an agent.",
-    "Model pins are NOT carried across: the profile names Anthropic aliases (sonnet/haiku), which are meaningless here and would either error or be silently ignored. Agents and commands inherit this runtime's own model selection instead."
-  ],
-  "scopes": {
-    "global": {
-      "root": "~/.config/opencode",
-      "core": "~/.cohorte/opencode",
-      "commands": "~/.config/opencode/commands",
-      "agents": "~/.config/opencode/agents",
-      "hooks": null,
-      "workflows": null,
-      "settings": null
-    },
-    "project": {
-      "root": ".opencode",
-      "core": ".cohorte/opencode",
-      "commands": ".opencode/commands",
-      "agents": ".opencode/agents",
-      "hooks": null,
-      "workflows": null,
-      "settings": null
-    }
-  },
-  "exclude_commands": [],
-  "command": {
-    "format": "md",
-    "ext": ".md",
-    "frontmatter": [
-      "description",
-      "agent",
-      "subtask"
-    ],
-    "args": "$ARGUMENTS",
-    "invoke": "/<name>"
-  },
-  "agent": {
-    "format": "md",
-    "frontmatter": [
-      "description",
-      "mode"
-    ],
-    "defaults": {
-      "mode": "subagent"
-    },
-    "dispatch": "address the subagent with @<name> and give it the full brief in one message",
-    "address": "@<name>",
-    "ext": ".md"
-  },
-  "capabilities": {
-    "subagents": true,
-    "hooks": false,
-    "workflows": false,
-    "inline_design": false,
-    "mcp": true,
-    "tool_restriction": false
-  },
-  "memory": "AGENTS.md",
-  "headless": "opencode run",
-  "hook": null
-}

package/core/templates/agent-handoff.md

@@ -1,34 +0,0 @@
-# HANDOFF — <surface> · <feature_id>
-
-<!-- REFERENCE COPY — not read at runtime. The AUTHORITATIVE shape is inlined in
-     core/agents/implementer.template.md (§"Your return"), because a rendered agent must
-     not need a second file read to know its own output format. This file exists for humans
-     reading the core; keep it byte-aligned with the template, or delete both together.
-
-     Keep it tight: the lead only acts on mismatches, test failures, remediation ticks, and TODOs.
-     Never list files one by one — the lead has `git diff --stat`. Never paste code excerpts —
-     a file:line reference is enough, the code is on disk. One line per item. -->
-
-## Summary
-
-<2–4 lines: what you built and the approach>
-
-## Migrations / schema (only if any)
-
-- `<name>` — <additive change>
-
-## Tests
-
-- Run: <this surface's test_cmd> · result: <pass/fail + counts>
-
-## Contract mismatches / assumptions
-
-<none, or describe — NEVER edit the contract; report here instead>
-
-## Remediation addressed (fix loops only)
-
-- <which `## Remediation` items you fixed, by file:line>
-
-## TODO / not done
-
-- <anything deferred, blocked, or out of scope — or "none">

package/core/templates/brainstorm-return.md

@@ -1,36 +0,0 @@
-# BRAINSTORM RETURN — <feature title>
-
-> Paste this into `/cohorte-spec`.
-
-**One-liner:** <what we're building, in one sentence>
-
-## Problem & value
-
-<the problem, who has it, why it matters>
-
-## Scope
-
-- **In:** <…>
-- **Out (non-goals):** <…>
-
-## Roles affected
-
-> Only if the profile has `rbac.enabled` — list the roles from `PIPELINE.md` §rbac and what each does;
-> explicitly note the lowest-privilege experience. Omit this section if there is no RBAC.
-
-<which roles do what>
-
-## Rough shape
-
-- **Data:** <entities / fields touched>
-- **Screens:** <key screens/flows — mobile-first if the project has UI>
-- **Interface (rough):** <endpoints / methods we'll need — refined into the contract in /cohorte-spec>
-
-## Risks & open questions
-
-- <risk / unknown>
-- <open question for /cohorte-spec to resolve>
-
-## Panel dissent (what was contested)
-
-<the strongest disagreement the panel surfaced — so /cohorte-spec doesn't paper over it>

package/core/templates/decisions.template.md

@@ -1,42 +0,0 @@
-# Decisions
-
-> The project's **transverse decision journal** — the non-obvious rules a stateless agent would
-> otherwise re-discover or contradict, one feature at a time. `PIPELINE.md` says *how this repo is
-> built* (surfaces, commands, conventions); this file says *what was decided and why*.
->
-> **Append-only. One line per decision. No prose blocks, no code.** The bound is the point: this file
-> is read by `/cohorte-spec`, `/cohorte-brainstorm` and `/cohorte-audit` — the deciding stages — and by **nothing else**.
-> Implementers and reviewers never read it: they work from the frozen contract, which already tells
-> them what to do; handing them the rationale too would cost `surfaces × dispatches` tokens per
-> feature for a fact they cannot act on.
->
-> Line shape (≤ ~160 chars, `·`-separated, no wrapping):
->
-> ```
-> - <YYYY-MM-DD> · <area> · <the decision, imperative> — because <the reason> · <feature_id>
-> ```
->
-> `<area>` is a short tag, not a path: `auth`, `data`, `api`, `ui`, `deploy`, `naming`, `surfaces`…
->
-> **Reversing a decision** never edits or deletes a line — append a superseding one and move the old
-> one to `## Superseded`:
->
-> ```
-> - <YYYY-MM-DD> · <area> · <the new decision> — because <reason> · supersedes <YYYY-MM-DD> <area> · <feature_id>
-> ```
->
-> **Keep it bounded:** when `## Live` passes ~100 lines, move every superseded line into
-> `## Superseded` (the audit trail survives; the section the deciding stages actually read stays
-> short). Never summarize or merge live lines — a decision either holds or has been superseded.
->
-> **What does NOT belong here:** anything the code, the tests, `PIPELINE.md` §Conventions or a spec
-> already states; a feature-local choice (that lives in its spec); a task, a TODO or a finding (those
-> are `## Remediation` and `specs/refactor-backlog.md`).
-
-## Live
-
-<!-- newest last -->
-
-## Superseded
-
-<!-- moved here when a line above supersedes them; never deleted -->

package/core/templates/design-brief.md

@@ -1,44 +0,0 @@
-# DESIGN BRIEF — <feature title> (`<feature_id>`)
-
-> The "spec return". This is §8 of the frozen spec, standalone — `/cohorte-spec` writes it to
-> `specs/design/<feature_id>.md` on freeze. Omit entirely if the project has no UI.
->
-> **Getting it into the design tool.** By default: paste it there yourself (see `PIPELINE.md` §design).
-> With `design.inline: true`, `/cohorte-spec` instead offers to hand this file straight to `/design`,
-> which reads the codebase, matches the existing UI style, and returns editable artboards in-session.
->
-> Inline changes who does the pasting, and nothing else. This file is still written to disk first and
-> is still what `/cohorte-build` reads — the artboards are an aid to the human, not an input to the
-> pipeline, and `/design` is a research preview that does not save them for you. Export anything worth
-> keeping before the session ends. If the design floor is unmet, the flag degrades to the paste-it-
-> yourself path with a note, never to an error: a brief that exists is worth more than a step that ran.
-
-**Goal:** <one line — what the user accomplishes>
-
-**Design system:** use the existing UI kit (`PIPELINE.md` §design → `ui_kit_path`). Mobile-first.
-
-## Screens / views
-
-For each: purpose, who sees it (role, if RBAC), and the key elements.
-
-- **<screen name>** — <purpose> · roles: <…>
-  - Elements: <…>
-  - States: empty · loading · error · success
-
-## Flows
-
-<step-by-step of the main user journey, and any role-specific variation>
-
-## Responsive
-
-- Mobile (base): <layout>
-- Tablet (`md:`): <changes>
-- Desktop (`lg:`): <changes>
-
-## Data shown
-
-<what fields/values appear on screen — must match the contract in spec §5>
-
-## Notes / constraints
-
-<accessibility · copy in the profile's `ui_language` · edge cases · theming constraints>

package/core/templates/patch.template.md

@@ -1,86 +0,0 @@
----
-feature_id: patch-<slug>
-kind: patch # a bug fix, not a feature — /cohorte-build skips contract authoring, /cohorte-ship commits `fix(…)`
-title: <one line: the bug, from the user's side>
-status: draft # draft → frozen → in-progress → in-review → shipped · blocked (see SCHEMA.md §Spec status)
-severity: <critical | major | minor> # drives nothing mechanical; it is what the human triages on
-branch: <patch_branch_prefix><feature_id>
-created: <YYYY-MM-DD>
-reviewed_base: # merge-base sha at the last SHIP verdict — freshness-gate anchor (written by /cohorte-review)
-reviewed_digest: # sha256 (16 hex) of the reviewed source diff vs reviewed_base, specs excluded — /cohorte-ship re-checks
-design_files: [] # omit unless the fix is itself visual
----
-
-# <one line: the bug, from the user's side>
-
-## 1. Symptom & repro
-
-> What the user sees, and the shortest deterministic path to see it. A repro nobody can run is a
-> hypothesis, not a bug — say so here rather than pretending otherwise.
-
-- **Observed:** …
-- **Expected:** …
-- **Repro:** 1. … 2. … 3. …
-- **Since / trigger:** <version, commit, or "unknown">
-
-## 2. Impact
-
-> Who is affected, how often, and whether there is a workaround. This is what justifies the patch
-> jumping the feature queue — one or two lines.
-
-## 3. Cause
-
-> Confirmed or hypothesis — label which. Name the `file:line` if you have it. If the cause is
-> unknown at freeze, say so: the implementer's first job is then to find it, and the review will
-> check that the stated cause matches the diff.
-
-## 4. Regression test (red first)
-
-> The heart of a patch spec — it replaces §5 CONTRACT as the thing the diff is checked against.
-> Name the test file and what it asserts. It must fail on the current code and pass after the fix.
-
-- **Test:** `<path/to/test>` · asserts: …
-- **Fails today because:** …
-
-## 5. Contract delta
-
-> Usually `none`. A fix that *changes* an existing contract entry describes the change here and
-> `/cohorte-build` propagates it to every surface that names it. A fix that needs **new** contract
-> surface area is not a patch — stop and run `/cohorte-spec` instead.
-
-`none`
-
-## 6. Surface tasks
-
-> One `###` subsection per surface the fix touches — a patch may legitimately span several (an
-> unvalidated field on the API *and* the form that sends it). Each TDD: the §4 test first.
-
-### <surface.key>
-
-- …
-
-## 7. Out of scope
-
-> The adjacent things this patch deliberately does NOT fix. This is the section that keeps a bug fix
-> from turning into a refactor — the reviewer reads it before flagging what you left alone. Real but
-> out-of-scope findings belong in `specs/refactor-backlog.md`, not in this diff.
-
-- …
-
-## 9. Acceptance criteria / DoD
-
-> §9, not §8 — the number is load-bearing, so don't renumber it. `review.md` and
-> `implementer.template.md` both name "contract §5, acceptance §9" verbatim, so a patch spec pins
-> those two sections to the feature spec's numbers and just has no §8 (the feature spec has no §7 —
-> a gap in the sequence is normal here).
-
-- [ ] The §4 regression test exists, and failed before the fix
-- [ ] Each touched surface's tests (TDD) green
-- [ ] `PIPELINE.md` commands.lint · typecheck · test green
-- [ ] The repro in §1 no longer reproduces
-- [ ] Nothing outside §6's surfaces changed
-
-## Remediation
-
-> Filled by `/cohorte-fix` from a REVIEW REPORT; empty otherwise. Each item:
-> `[ ] <SEVERITY> · <file:line> · <spec-violation|quality|security> · <concrete fix>`

package/core/templates/pr-body.md

@@ -1,25 +0,0 @@
-## <type>(<scope>): <feature title>
-
-**feature_id:** `<feature_id>` · closes/relates: <issue if any>
-
-### What & why
-
-<2–4 lines: what this ships and the value, from the spec goal>
-
-### Changes
-
-> One bullet per surface (from `PIPELINE.md` §surfaces), plus the shared contract.
-
-- **<surface.key>:** <what changed>
-- **Shared:** `<contract.path>/<feature_id>.<ext>` <(new/changed types: names only; omit if contract.enabled is false)>
-
-### Tests
-
-- <per surface: test runner · coverage>
-- <PIPELINE.md commands.lint · typecheck · test> — green
-
-### Review
-
-Verdict: **SHIP** · remediation rounds: <n>
-
-🤖 Generated with [Claude Code](https://claude.com/claude-code)

package/core/templates/review-feedback.md

@@ -1,38 +0,0 @@
-# REVIEW REPORT
-
-<!-- REFERENCE COPY — not read at runtime. The AUTHORITATIVE shape is inlined in
-     core/agents/review.md (§"Your return"), because an agent must not need a second
-     file read to know its own output format. This file exists for humans reading the
-     core; keep it byte-aligned with the agent, or delete both together.
-
-     Everything in an HTML comment is guidance — do NOT emit it.
-     Verdict rules live in the review agent's instructions (SHIP = no CRITICAL/security;
-     REVISE = ≥1 CRITICAL; BLOCK = security vulnerability).
-     CAPPED: max 20 findings, ONE line each (severity · file:line · type · concrete fix),
-     ZERO code excerpts — file:line is enough, the source is on disk. Overflow ⇒ keep all
-     CRITICAL/HIGH/security, fill by severity, close with one `+<n> more …` line. -->
-
-feature_id: <feature_id> · scope: <surface.key>
-
-| Severity | Count |
-| -------- | ----- |
-| CRITICAL | 0     |
-| HIGH     | 0     |
-| MEDIUM   | 0     |
-| LOW      | 0     |
-
-Verdict: <SHIP | REVISE | BLOCK>
-
-## Findings
-
-<!-- Every finding self-sufficient for a stateless agent; order by severity; "None." if none.
-     The line format pastes straight into the spec's `## Remediation`. -->
-
-- **[CRITICAL]** `<surface.path>/...:42` · spec-violation · <what's wrong vs spec §X> → **Fix:** <concrete change>
-- **[HIGH]** `<path>:88` · quality · <issue> → **Fix:** <concrete change>
-- **[BLOCK/security]** `<path>:line` · security · <vuln> → **Fix:** <concrete change>
-
-## Notes
-
-<!-- ONLY the RBAC / mobile-first assessment when the profile enables them; omit the section
-     otherwise. Never list things verified clean. -->