chore: add anthropic vars to use local models with claude code (opt-in)

.ai/prompts/global.md

@@ -27,13 +27,24 @@ Before starting any implementation work:
 2. Run the project's test command to verify all tests pass.
 3. If either fails, investigate and fix before starting new work.
 
-## Linear workpad
+## Linear progress updates
 
-Use a single Linear comment as a persistent workpad:
+Post a new Linear comment for each milestone of your work — investigation
+findings, implementation decisions, results, guidance for the next
+stage, and so on. Do not try to maintain or find a single running
+comment to update:
 
-- Title: `## Workpad`
-- Update it at each milestone with: current status, decisions made, and next steps.
-- On rework runs, append the rework section — do not delete prior content.
+    mix lc issue comment <ISSUE_ID> --body-file <path>
+
+- Write the comment's full content to a file first, then pass its
+  path — never build a multi-line comment as an inline shell argument.
+- Each comment should stand on its own: describe only this step's
+  findings, decisions, and results, not the whole history. Read prior
+  comments for context (`mix lc issue ls --full <ISSUE_ID>`); post a new
+  one for what's new, don't try to edit an old one.
+- Always only use `mix lc` to interact with Linear — never call the
+  Linear API directly (curl, GraphQL, or otherwise). If `mix lc` is
+  broken, log that error and stop processing.
 
 ## Rework awareness
 
@@ -43,4 +54,5 @@ On rework runs, the workspace already contains prior work.  Check for:
 - An existing feature branch (do not create a new one)
 - An open PR (push to it, do not open a second)
 - Review comments requesting changes (address them specifically)
-- Prior workpad content (append to it, do not overwrite)
+- Prior progress comments (read them for context; post a new comment for
+  this run rather than editing an old one)

.ai/prompts/implement.md

@@ -18,6 +18,11 @@ No description provided.
 
 Implement the solution, create a PR, and ensure it passes all quality checks.
 
+## Rule
+
+Always sign git commits. If a gpg-agent is not available with a signing key,
+stop and note that on the linear issue, do not create an unsigned commit.
+
 ## First run
 
 1. Read the investigation summary from the Linear comments.
@@ -36,7 +41,7 @@ Implement the solution, create a PR, and ensure it passes all quality checks.
    gh pr create --title "{{ issue.identifier }}: <concise title>" --body "<description>"
    ```
 8. Link the PR to the Linear issue.
-9. Update the workpad with: what was done, what was tested, any known limitations.
+9. Post a Linear comment with: what was done, what was tested, any known limitations.
 
 ## Rework run
 
@@ -57,7 +62,7 @@ If this is a rework run (a branch and PR already exist):
    - Which review comments were addressed
    - What was modified
    - Any decisions or trade-offs
-7. Append a rework section to the Linear workpad.
+7. Post a Linear comment summarising the rework.
 
 ## Quality bar
 
@@ -68,4 +73,4 @@ Before finishing, verify:
 - [ ] No lint errors
 - [ ] All acceptance criteria from the ticket description met
 - [ ] PR created (or updated) and linked to Linear issue
-- [ ] Workpad updated with completion summary
+- [ ] Linear comment posted with a completion summary

.ai/prompts/investigate.md

@@ -31,7 +31,6 @@ an investigation summary posted as a Linear comment — not code changes.
    - **Risks or open questions**
    - **Proposed approach** (high-level, 3-5 bullet points)
 6. Post the summary as a Linear comment titled `## Investigation`.
-7. Update the workpad with investigation status.
 
 ## Rework run
 
@@ -41,8 +40,8 @@ If this is a rework run (the workspace already has investigation content):
 2. Read your prior investigation summary.
 3. Address the specific feedback — expand analysis, correct mistakes, or
    investigate additional areas as requested.
-4. Update the `## Investigation` comment with revised findings.
-5. Append a rework note to the workpad.
+4. Post a new Linear comment titled `## Investigation (rework)` with the
+   revised findings — do not try to edit the prior comment.
 
 ## Do NOT
 

.ai/prompts/merge.md

@@ -26,8 +26,9 @@ mechanical stage — no new code changes.
    ```
    gh pr merge <number> --squash --delete-branch
    ```
-5. Update the Linear workpad with the merge confirmation.
-6. Move the Linear issue to `Done`.
+5. Always use `mix lc issue` to interact with Linear issues
+6. Post a Linear comment with the merge confirmation.
+7. Move the Linear issue to `Done`.
 
 ## Rework run
 
@@ -43,10 +44,11 @@ If this is a rework run (merge was attempted before but failed):
    - If it is a test failure caused by the PR's changes, post details to
      Linear and stop (this needs to go back to implementation).
    - If it is a flaky or infrastructure issue, re-run and retry the merge.
-4. Update the workpad with what happened.
+4. Post a Linear comment with what happened.
 
 ## Do NOT
 
 - Make code changes beyond conflict resolution.
 - Open new PRs.
 - Skip CI checks.
+- Use anything other than `mix lc` to interact with Linear

.ai/prompts/review.md

@@ -39,6 +39,7 @@ the implementer missed — not to rubber-stamp the PR.
    - Linting
    - Tests
 6. Post your review as a Linear comment titled `## Code Review`:
+   - Always only use `mix lc issue` to interact with Linear
    - List issues found (critical, major, minor)
    - Note anything that looks good
    - Give an overall assessment: approve, request changes, or flag concerns

.gitmodules

@@ -27,4 +27,4 @@
 	url = git@github.com:fuelen/owl
 [submodule "vendor/stokowski"]
 	path = vendor/stokowski
-	url = https://github.com/Sugar-Coffee/stokowski
+	url = git@github.com:bougyman/stokowski

AGENTS.md

@@ -14,9 +14,31 @@ and best practices for agents to follow.
 - Phase 9 Plan: documents/phase-9-plan.adoc
 - Phase 10 Plan: documents/phase-10-plan.adoc
 - Phase 11 Plan: documents/phase-11-plan.adoc
+- Phase 12 Plan: documents/phase-12-plan.adoc
+- Phase 13 Plan: documents/phase-13-plan.adoc
 
 ## Project Structure
 
+### Linear Team and Project
+
+The `Linear CLI` project of the "Elixir Traitors" (`EXT`) team on the
+https://linear.app/the-rubyists[Rubyists Linear Organization] manages
+the project roadmap and issue tracking.
+
+#### Rules for Interacting with Linear
+
+Always only use `mix lc` to interact with linear.app. Do not look for an
+mcp or any other way to interact with issues or the project.
+
+`mix lc --help`
+`mix lc issue --help`
+`mix lc issue list --help`
+`mix lc issue create --help`
+`mix lc issue status --help`
+`mix lc issue comment --help`
+
+This should be enough to get started
+
 ### Repository layout
 
 This repo uses two Mix projects side-by-side, not nested:

Readme.adoc

@@ -160,6 +160,7 @@ so you don't have to type the full name every time:
 |`issue assign` |`a`
 |`issue move` |`m`, `mv`
 |`issue update` |`u`
+|`issue comment` |
 |`issue pr` |`pull-request`
 |`team list` |`l`, `ls`
 |`project list` |`l`, `ls`
@@ -289,6 +290,22 @@ $ lcomment CRY-1234 CRY-3 <5>
 <4> Opens your editor for the comment (use `-` to prompt)
 <5> Always prompts for a comment (`lcomment` is a wrapper for `lc issue update --comment -`)
 
+===== Add a comment from a file (`issue comment`)
+
+Same plain create as `issue update --comment`/`lcomment`, plus
+`--body-file` — the way to supply a large multi-line body without
+building it as a single shell argument.
+
+[source,sh]
+----
+$ lc issue comment CRY-1234 -m "Here is a comment" <1>
+$ lc issue comment CRY-1234 --body-file notes.md <2>
+$ lc issue comment CRY-1234 --body-file - <3>
+----
+<1> Plain create, same as `issue update --comment`
+<2> Reads the body from a file
+<3> Reads the body from stdin
+
 ===== Close one or many issues
 
 Use `--status`/`-s` to choose the completed or cancelled workflow state by

app/lib/linear_cli/cli.ex

@@ -212,6 +212,10 @@ defmodule LinearCli.CLI do
 
   defp dispatch([:issue, :pr], result, halt), do: run(&Commands.issue_pr/1, result, halt)
   defp dispatch([:issue, :move], result, halt), do: run(&Commands.issue_move/1, result, halt)
+
+  defp dispatch([:issue, :comment], result, halt),
+    do: run(&Commands.issue_comment/1, result, halt)
+
   defp dispatch([:issue, :take], result, halt), do: run(&Commands.issue_take/1, result, halt)
   defp dispatch([:issue, :status], result, halt), do: run(&Commands.issue_status/1, result, halt)
   defp dispatch([:issue, :update], result, halt), do: run(&Commands.issue_update/1, result, halt)
@@ -738,6 +742,24 @@ defmodule LinearCli.CLI do
                 description: [long: "--description", help: "The description of the PR"]
               ]
             ],
+            comment: [
+              name: "comment",
+              about: "Add a comment to an issue",
+              args: [
+                issue_id: [value_name: "ISSUE_ID", help: "The Issue (i.e. CRY-1)", required: true]
+              ],
+              options: [
+                comment: [
+                  short: "-m",
+                  long: "--comment",
+                  help: "Comment text. - opens an editor"
+                ],
+                body_file: [
+                  long: "--body-file",
+                  help: "Read the comment body from this file (- for stdin) instead of --comment"
+                ]
+              ]
+            ],
             status: [
               name: "status",
               about: "Change workflow state (ISSUE_ID...)",

app/lib/linear_cli/cli/commands.ex

@@ -519,6 +519,55 @@ defmodule LinearCli.CLI.Commands do
     end
   end
 
+  @doc """
+  Adds a comment to a single issue.
+
+  `--comment`/`-m` and `--body-file` are mutually exclusive. `--body-file`
+  reads the body from a file (`-` for stdin) - the way to supply a large
+  multi-line body without building it as a single shell argument, which
+  is what `--comment`, going through
+  `LinearCli.CLI.WhatFor.comment_for/2`'s prompt/editor resolution, does
+  not protect against. Without either option, `comment_for/2`'s existing
+  behavior applies (prompt, or open an editor for `-`).
+
+  Calls `Linear.add_comment/2` directly rather than
+  `LinearCli.CLI.IssueHelpers.issue_comment/2` so the confirmation can be
+  suppressed under `--output json` - matching how `print_move_results/3`
+  suppresses its own confirmation for `issue move --output json`.
+
+  New in this port - Ruby has no equivalent.
+  """
+  @spec issue_comment(Optimus.ParseResult.t()) :: :ok | {:error, term()}
+  def issue_comment(%{args: %{issue_id: issue_id}, options: options}) do
+    with :ok <- validate_comment_options(options),
+         {:ok, comment_text} <- resolve_comment_body(options),
+         {:ok, [issue]} <- Linear.issues(%{ids: [IssueHelpers.expand_issue_id(issue_id)]}),
+         body = WhatFor.comment_for(issue, comment_text),
+         {:ok, comment} <- Linear.add_comment(issue.identifier, body) do
+      unless options.output == "json", do: Prompt.ok("Comment added to #{issue.identifier}")
+      Display.show(comment, %{output: options.output})
+      :ok
+    end
+  end
+
+  defp validate_comment_options(%{comment: comment, body_file: body_file})
+       when not is_nil(comment) and not is_nil(body_file) do
+    {:error, {:smells_bad, "give --comment or --body-file, not both"}}
+  end
+
+  defp validate_comment_options(_options), do: :ok
+
+  defp resolve_comment_body(%{body_file: nil, comment: comment}), do: {:ok, comment}
+  defp resolve_comment_body(%{body_file: "-"}), do: {:ok, read_stdin()}
+  defp resolve_comment_body(%{body_file: path}), do: File.read(path)
+
+  defp read_stdin do
+    case IO.read(:stdio, :eof) do
+      :eof -> ""
+      data -> data
+    end
+  end
+
   @doc """
   Moves issues to a target project.
 

app/lib/linear_cli/cli/display.ex

@@ -7,7 +7,7 @@ defmodule LinearCli.CLI.Display do
   own `#to_s`/`#full`/`#display` methods.
   """
 
-  alias LinearCli.Linear.{Issue, Project, ProjectUpdate, Team, User}
+  alias LinearCli.Linear.{Comment, Issue, Project, ProjectUpdate, Team, User}
   alias LinearCli.Profiles.Profile
 
   @ash_internal_fields ~w(__meta__ __metadata__ __order__ __lateral_join_source__ aggregates calculations)a
@@ -37,6 +37,15 @@ defmodule LinearCli.CLI.Display do
     IO.puts("Posted#{health}: #{update.url}")
   end
 
+  # New in this port - Ruby has no equivalent (no bare `Comment` command
+  # existed to display one). `LinearCli.CLI.IssueHelpers.issue_comment/2`/
+  # `upsert_comment/4` already print a "Comment added to.../updated on..."
+  # confirmation via `Prompt.ok/1` before this runs, so this only needs to
+  # add the one thing that isn't in that line: a link to the comment.
+  defp puts_text(%Comment{} = comment, _opts) do
+    IO.puts(comment.url || "(no URL returned)")
+  end
+
   defp puts_text(%Profile{} = profile, _opts) do
     marker = if profile.active, do: "* ", else: "  "
 

app/mix.lock

@@ -1,5 +1,5 @@
 %{
-  "ash": {:hex, :ash, "3.31.3", "b36672bff745eadd52265d8b0a303f98ba26a31173f4116ebd2df7be0cbafeff", [:mix], [{:crux, ">= 0.1.2 and < 1.0.0-0", [hex: :crux, repo: "hexpm", optional: false]}, {:decimal, "~> 2.0 or ~> 3.0", [hex: :decimal, repo: "hexpm", optional: false]}, {:ecto, "~> 3.14", [hex: :ecto, repo: "hexpm", optional: false]}, {:ets, "~> 0.8", [hex: :ets, repo: "hexpm", optional: false]}, {:igniter, ">= 0.6.29 and < 1.0.0-0", [hex: :igniter, repo: "hexpm", optional: true]}, {:jason, ">= 1.0.0", [hex: :jason, repo: "hexpm", optional: false]}, {:picosat_elixir, "~> 0.2", [hex: :picosat_elixir, repo: "hexpm", optional: true]}, {:plug, ">= 0.0.0", [hex: :plug, repo: "hexpm", optional: true]}, {:reactor, "~> 1.0", [hex: :reactor, repo: "hexpm", optional: false]}, {:simple_sat, ">= 0.1.1 and < 1.0.0-0", [hex: :simple_sat, repo: "hexpm", optional: true]}, {:spark, ">= 2.6.0", [hex: :spark, repo: "hexpm", optional: false]}, {:splode, "~> 0.3", [hex: :splode, repo: "hexpm", optional: false]}, {:stream_data, "~> 1.0", [hex: :stream_data, repo: "hexpm", optional: false]}, {:telemetry, "~> 1.1", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm", "4c105da2080475d114908c32e70970e69c857a9068a577a4e99dbf2801baa11e"},
+  "ash": {:hex, :ash, "3.32.3", "a6390b9f6497458f4575220cd507b6b5aae52c43bba0cc057aa3fa96e44ef416", [:mix], [{:crux, ">= 0.1.2 and < 1.0.0-0", [hex: :crux, repo: "hexpm", optional: false]}, {:decimal, "~> 2.0 or ~> 3.0", [hex: :decimal, repo: "hexpm", optional: false]}, {:ecto, "~> 3.14", [hex: :ecto, repo: "hexpm", optional: false]}, {:ets, "~> 0.8", [hex: :ets, repo: "hexpm", optional: false]}, {:igniter, ">= 0.6.29 and < 1.0.0-0", [hex: :igniter, repo: "hexpm", optional: true]}, {:jason, ">= 1.0.0", [hex: :jason, repo: "hexpm", optional: false]}, {:picosat_elixir, "~> 0.2", [hex: :picosat_elixir, repo: "hexpm", optional: true]}, {:plug, ">= 0.0.0", [hex: :plug, repo: "hexpm", optional: true]}, {:reactor, "~> 1.0", [hex: :reactor, repo: "hexpm", optional: false]}, {:simple_sat, ">= 0.1.1 and < 1.0.0-0", [hex: :simple_sat, repo: "hexpm", optional: true]}, {:spark, ">= 2.6.0", [hex: :spark, repo: "hexpm", optional: false]}, {:splode, "~> 0.3", [hex: :splode, repo: "hexpm", optional: false]}, {:stream_data, "~> 1.0", [hex: :stream_data, repo: "hexpm", optional: false]}, {:telemetry, "~> 1.1", [hex: :telemetry, repo: "hexpm", optional: false]}], "hexpm", "4eebbd3fa7dab05d0aab9c7552155c07e746b18c8dc1cf5ed2f62195cea87f3d"},
   "bunt": {:hex, :bunt, "1.0.0", "081c2c665f086849e6d57900292b3a161727ab40431219529f13c4ddcf3e7a44", [:mix], [], "hexpm", "dc5f86aa08a5f6fa6b8096f0735c4e76d54ae5c9fa2c143e5a1fc7c1cd9bb6b5"},
   "burrito": {:hex, :burrito, "1.6.0", "7af0a75f11680e8a6e9c01370c9af51cb9d0e15b3226eddf4f438dbc68570520", [:mix], [{:jason, "~> 1.4", [hex: :jason, repo: "hexpm", optional: false]}, {:req, ">= 0.5.0", [hex: :req, repo: "hexpm", optional: false]}, {:typed_struct, "~> 0.2.0 or ~> 0.3.0", [hex: :typed_struct, repo: "hexpm", optional: false]}], "hexpm", "e636a00b032c45a69ff755d9fc53fa5fdc9e1d21bdbd229075fe4a15b05355fe"},
   "castore": {:hex, :castore, "1.0.21", "0a0e8330dc267a40a3b7ad86d39302764bb71758172904e6a59d5ad6443ce307", [:mix], [], "hexpm", "e42e22723e25dbd46876d056a03f685513d6e98f6b5e555dc551321decd76c5c"},
@@ -45,7 +45,7 @@
   "protobuf": {:hex, :protobuf, "0.16.1", "7bf0c3e6b24fd297e2e3722ecb985c3900bcc55d004b7faf0737e248c3e64691", [:mix], [{:jason, "~> 1.2", [hex: :jason, repo: "hexpm", optional: true]}], "hexpm", "97fb9f1fe48c38c4ebfc0f8a7a20adb22b2491bbfbdb192fab9a6821d5d604e1"},
   "purl": {:hex, :purl, "0.3.0", "b6e2f792e944007ed474299e56ea43ea4819f064a4a4f67e4153e1ba02d066de", [:mix, :rebar3], [{:stream_data, "~> 1.1", [hex: :stream_data, repo: "hexpm", optional: true]}], "hexpm", "158cf2c0533517fe0d68752bd790392f065c5ffdfbde38524890066ebe640302"},
   "reactor": {:hex, :reactor, "1.0.6", "546a87255693bcee99451d022cc86927161cdb527f5216d4dcac2b31e08eb122", [:mix], [{:igniter, "~> 0.4", [hex: :igniter, repo: "hexpm", optional: true]}, {:iterex, "~> 0.1", [hex: :iterex, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}, {:multigraph, "~> 0.16.1-mg.2", [hex: :multigraph, repo: "hexpm", optional: false]}, {:spark, ">= 2.3.3 and < 3.0.0-0", [hex: :spark, repo: "hexpm", optional: false]}, {:splode, "~> 0.2", [hex: :splode, repo: "hexpm", optional: false]}, {:telemetry, "~> 1.2", [hex: :telemetry, repo: "hexpm", optional: false]}, {:yaml_elixir, "~> 2.11", [hex: :yaml_elixir, repo: "hexpm", optional: false]}, {:ymlr, "~> 5.0", [hex: :ymlr, repo: "hexpm", optional: false]}], "hexpm", "e3f8fd8e870c2b011316ca2ac422bb4bc710cac9f02c578f8526f7a6348d932b"},
-  "req": {:hex, :req, "0.7.2", "364eae2e5f5c984f2dac6d71c07f8c8c89ce0bc49c4d746dacb7a306823020de", [:mix], [{:brotli, "~> 0.3.1", [hex: :brotli, repo: "hexpm", optional: true]}, {:finch, "~> 0.21", [hex: :finch, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}, {:mime, "~> 2.0.6 or ~> 2.1", [hex: :mime, repo: "hexpm", optional: false]}, {:nimble_csv, "~> 1.0", [hex: :nimble_csv, repo: "hexpm", optional: true]}, {:plug, "~> 1.0", [hex: :plug, repo: "hexpm", optional: true]}], "hexpm", "c9cdfa276b05d8db2a27fda5d233e6858b764d47189d76cbb186e130a871ae0b"},
+  "req": {:hex, :req, "0.7.4", "23e9ffec17de032a46a4b15ed65c09793893bf4a7c680f4bbf6227fce6bdf74d", [:mix], [{:brotli, "~> 0.3.1", [hex: :brotli, repo: "hexpm", optional: true]}, {:finch, "~> 0.21", [hex: :finch, repo: "hexpm", optional: false]}, {:jason, "~> 1.0", [hex: :jason, repo: "hexpm", optional: false]}, {:mime, "~> 2.0.6 or ~> 2.1", [hex: :mime, repo: "hexpm", optional: false]}, {:nimble_csv, "~> 1.0", [hex: :nimble_csv, repo: "hexpm", optional: true]}, {:plug, "~> 1.0", [hex: :plug, repo: "hexpm", optional: true]}], "hexpm", "4b192d63253e8dcc6221ef992ea9ebef7d3555166e8423aa5b553e86bc3c69a2"},
   "rewrite": {:hex, :rewrite, "1.3.0", "67448ba7975690b35ba7e7f35717efcce317dbd5963cb0577aa7325c1923121a", [:mix], [{:glob_ex, "~> 0.1", [hex: :glob_ex, repo: "hexpm", optional: false]}, {:sourceror, "~> 1.0", [hex: :sourceror, repo: "hexpm", optional: false]}, {:text_diff, "~> 0.1", [hex: :text_diff, repo: "hexpm", optional: false]}], "hexpm", "d111ac7ff3a58a802ef4f193bbd1831e00a9c57b33276e5068e8390a212714a5"},
   "rustler_precompiled": {:hex, :rustler_precompiled, "0.8.4", "700a878312acfac79fb6c572bb8b57f5aae05fe1cf70d34b5974850bbf2c05bf", [:mix], [{:castore, "~> 0.1 or ~> 1.0", [hex: :castore, repo: "hexpm", optional: false]}, {:rustler, "~> 0.23", [hex: :rustler, repo: "hexpm", optional: true]}], "hexpm", "3b33d99b540b15f142ba47944f7a163a25069f6d608783c321029bc1ffb09514"},
   "sbom": {:hex, :sbom, "0.10.0", "b99be5407bc196d0ad71b8061126a67aae46dc3bfaa852b4c1c04645dd1ad984", [:mix], [{:hex_core, "~> 0.15.0", [hex: :hex_core, repo: "hexpm", optional: false]}, {:jason, "~> 1.4", [hex: :jason, repo: "hexpm", optional: true]}, {:optimus, "~> 0.6.1", [hex: :optimus, repo: "hexpm", optional: false]}, {:protobuf, "~> 0.16.0", [hex: :protobuf, repo: "hexpm", optional: false]}, {:purl, "~> 0.3.0", [hex: :purl, repo: "hexpm", optional: false]}], "hexpm", "a8116ef965c1ebd103e223545794bd0a6691edd3ec678ec07972d473e2badc95"},