opencode-thrum-pro 0.1.6 → 0.1.8

package/assets/skills/thrum/resources/CLI_REFERENCE.md

@@ -255,7 +255,7 @@ Flags:
 --runtime string         Runtime preset: claude, codex, cursor, gemini, opencode, auggie, cli-only
 --preamble-file string   Custom preamble file to compose with default preamble
 --no-init                Skip runtime config generation, just register agent
---force                  Overwrite existing runtime config files
+--force                  Force runtime config reinitialization; project instruction files are preserved
 --dry-run                Preview changes without writing files or registering
 --no-agent-pid           Persist agent_pid=0 instead of detecting the runtime ancestor; defers PID claim to first /thrum:prime (used for inline tmux quickstart)
 ```
@@ -379,6 +379,10 @@ thrum agent delete <name>
 thrum agent delete coordinator_1B9K --force
 ```
 
+Refuses an agent whose linked worktree still exists (run `worktree teardown`
+first), a live pid/tmux process, and coordinators. Order: teardown (with
+salvage), then delete.
+
 Flags:
 
 ```text
@@ -858,7 +862,7 @@ thrum tmux cancel <command-id>                 # Cancel a queued or active comma
 --intent string    Initial work intent description
 --runtime string   Runtime preset: claude, codex, cursor, gemini, opencode, auggie
 --no-agent         Skip agent registration (create session only)
---force            Overwrite existing runtime config files
+--force            Re-register even if agent exists; kill and recreate an existing session
 ```
 
 Without `--no-agent`, the command errors if `--name`, `--role`, and `--module`
@@ -900,7 +904,7 @@ thrum worktree create <name> --detach          # Detached HEAD worktree
 thrum worktree create <name> \
   --name <agent> --role <role> --module <mod>  # Create worktree + register agent
 thrum worktree setup <name>                    # Alias for worktree create
-thrum worktree teardown <name>                       # Remove worktree, keep branch
+thrum worktree teardown <name>                       # Retire agent + remove worktree, keep branch (does NOT delete the agent; reap with `thrum agent delete` after)
 thrum worktree teardown <name> --delete-branch       # Also delete the worktree's branch
 thrum worktree list                                  # List worktrees with agent info
 ```
@@ -939,51 +943,52 @@ later.
 
 ## Monitor Jobs
 
-Run a long-lived command, filter output through a regex, and deliver matching
-lines as Thrum messages. Jobs persist across daemon restarts. Max 100
-concurrent. The command must follow `--`.
+Run a command, filter its output through a regex, and deliver matching lines as
+Thrum messages. Without `--schedule` the command runs continuously and restarts
+with backoff; with `--schedule` it runs once per cron tick. Jobs persist across
+daemon restarts. Max 100 concurrent. The command must follow `--`.
 
 ```bash
 thrum monitor start --name <n> --match <re> --to @agent -- <cmd> [args...]
 thrum monitor start --name <n> --match <re> --to @agent \
-  --debounce 120s --env KEY=VALUE -- <cmd>
+  --schedule "*/5 * * * *" --notify-on-success --debounce 120s --env KEY=VALUE -- <cmd>
 thrum monitor list                             # Running jobs only
 thrum monitor list --all                       # Include stopped/dead (<1 week)
 thrum monitor show <id|name>                   # Full detail (env values redacted)
-thrum monitor stop <id|name>                   # SIGTERM → 5s → SIGKILL
-thrum monitor logs <id|name>                   # Last 20 matched lines
-thrum monitor logs <id|name> -n 50             # Last 50 matched lines
+thrum monitor logs <id|name> -n 50             # Last 50 matched lines (default 20)
+thrum monitor update <id|name> --match <re>    # Change match/schedule/target/debounce in place
+thrum monitor stop <id|name>                   # SIGTERM, 5s, SIGKILL
 thrum monitor restart <id|name>                # Restart dead/stopped monitor
+thrum monitor delete <id|name>                 # Remove the record and free the name
+thrum monitor adopt <id|name>                  # Claim a monitor for this daemon
 ```
 
-Note: `monitor add` is retained as an alias for `monitor start`.
+`monitor add` is an alias for `monitor start`.
 
 `monitor start` flags:
 
 ```text
 --name string         Unique monitor name (required)
---match string        Regex pattern — matching lines trigger a message (required)
+--match string        Regex pattern - matching lines trigger a message (required)
 --to string           Target agent or group, e.g. @coordinator (required)
---debounce duration   Leading-edge debounce window, minimum 30s (default 60s)
---env strings         Environment variable in KEY=VALUE form (repeatable)
+--schedule string     5-field cron expression; runs the command once per tick
+--notify-on-success   Deliver a generic [OK] message for a successful run in which no line matched
+--debounce duration   Leading-edge debounce window, minimum 30s (default 1m)
+--env stringArray     Environment variable in KEY=VALUE form (repeatable)
 --cwd string          Working directory for the command (default: current dir)
 ```
 
-`monitor list` flags:
-
-```text
---all   Include stopped/dead monitors younger than one week
-```
+`monitor update` flags: `--match`, `--to`, `--schedule`, `--debounce`.
+`--schedule` changes the cron of a scheduled monitor at any time; setting or
+removing a schedule switches the mode, which is refused while the monitor is
+running and allowed while it is stopped.
 
-`monitor logs` flags:
-
-```text
--n, --limit int   Max number of matches to return (default 20)
-```
+`monitor logs` flag: `-n, --limit int` (default 20).
 
-Key constraints: local Unix socket only, max line length 2KB (lines truncated),
-leading-edge debounce (min 30s), auto-persists across daemon restart, sends a
-notify-only message on child exit.
+Key constraints: local Unix socket only, lines over 2KB are truncated with a
+marker, one matching line is delivered per debounce window, and a message is
+sent when the child exits non-zero. See the `using-monitors` skill for
+reminders, script checks and delivery rules.
 
 ---
 

package/assets/skills/thrum-memory/SKILL.md

@@ -70,7 +70,7 @@ thrum memory edit <id> --short @newshort.md
 thrum memory edit <id> --add-tag v0.11 --rm-tag draft
 ```
 
-Link an edge:
+Link an edge. `memory create`, `edit` and `link` need a license (memory.substrate); reads, `delete`, `purge` and `unlink` do not.
 
 ```bash
 thrum memory link <new-id> supersedes <old-id>

package/assets/skills/using-monitors/SKILL.md

@@ -0,0 +1,198 @@
+---
+name: using-monitors
+description: "Use when scheduling a reminder, watching a log, or running a periodic check that must reach an agent - thrum monitor start, cron --schedule, --match, --notify-on-success, --debounce, recurring nudge, script check with exit codes, why a monitor message did not arrive, how to verify a monitor delivered."
+---
+
+# Thrum Monitors - Reminders And Script Checks
+
+## Overview
+
+A monitor runs a command, keeps the output lines that match a regex, and
+delivers them as Thrum messages to a target: a continuous monitor sends each
+kept line, a scheduled monitor sends all the lines of a run in one message. With
+`--schedule` it runs the command once per cron tick; without it the command runs continuously
+and restarts with backoff when it exits. Monitors persist across daemon
+restarts and run only on the daemon that owns them.
+
+Every flag below appears in `thrum monitor start --help`. Re-read the help
+before relying on a flag not listed here.
+
+## Command Surface
+
+```bash
+thrum monitor start --name <n> --match <re> --to @agent [--schedule "<cron>"] \
+  [--notify-on-success] [--debounce 60s] [--env K=V] [--cwd <dir>] -- <cmd> [args...]
+thrum monitor list [--all]
+thrum monitor show <name|id>
+thrum monitor logs <name|id> [-n 50]
+thrum monitor update <name|id> [--match <re>] [--to <t>] [--debounce <d>] [--schedule "<cron>"]
+thrum monitor stop <name|id>
+thrum monitor restart <name|id>
+thrum monitor delete <name|id>
+```
+
+- `--name`, `--match` and `--to` are required; the command follows `--`.
+- `--schedule` takes a 5-field cron expression. `update --schedule` changes the
+  cron of a scheduled monitor at any time. Setting a first schedule or removing
+  it (`--schedule ""`) switches the mode, which is refused while the monitor is
+  running and allowed while it is stopped.
+- `--debounce` is leading-edge with a 30s minimum (default 1m).
+- `stop` leaves a stopped record that still holds the name; `delete` frees the
+  name. Use a unique name per monitor.
+
+## What Is Delivered
+
+Each output line is tested against `--match` on its own. A line is truncated at
+2048 bytes with a marker appended.
+
+A scheduled (`--schedule`) job is a one-shot run, so its exit code is
+authoritative. It delivers ONE message at exit that carries every matched line,
+in order. A continuous job has no exit code per line, so it classifies and
+delivers and classifies each matched line on its own, by its words.
+
+| Scheduled job                                                   | Delivered as                                  |
+| --------------------------------------------------------------- | --------------------------------------------- |
+| Non-zero exit, or the command failed to start                   | `[FAIL] <name>: exit code N` with the output tail, then the matched lines |
+| Exit 0, a matched line starts `ERROR:`, `FATAL:` or `FAIL:`     | `[FAIL] <name>: matched error pattern` + all matched lines |
+| Exit 0, highest prefix is `WARN:`, `WARNING:` or `ALERT:`        | `[WARN] <name>: matched WARNING` + all matched lines |
+| Exit 0, lines matched, no such prefix                           | All matched lines, in order, verbatim         |
+| Exit 0, nothing matched, `--notify-on-success`                  | `[OK] <name>: succeeded`                      |
+| Exit 0, nothing matched                                         | Nothing (logged only)                         |
+
+Cadence: the first non-zero scheduled run sends its `[FAIL]` notice; repeats of
+that failure are not sent again until the outcome changes or the re-escalation
+interval (30 minutes) passes. An exit-0 run that matched lines sends its message
+on every run.
+
+On a scheduled job only these prefixes, at the very start of a line, label the
+output, with the colon directly after the word: `ERROR:`, `FATAL:` and `FAIL:`
+fail it; `WARN:`, `WARNING:` and `ALERT:` warn. Any other prefix, including
+`ALERT-<NAME>:`, `ERROR :`, `INFO:`, `OK:`, `NOT_OK:` and lowercase forms, is
+neutral. They are read before any wording in the body, and
+the highest one decides the label. Words such as `done`, `ok`, `complete`, `failures` or `error` neither
+drop nor relabel a line, and `WARN: batch not complete` stays a warning.
+`--notify-on-success` adds the generic `[OK]` only for a run in which nothing
+matched; an empty matched line counts as a match and is announced as
+`[matched N empty line(s)]`.
+
+The whole message, including its label and framing, never exceeds the daemon's
+configured message-body limit. Matched lines are sent whole while they fit both
+budgets: the in-memory retention budget (each line costs its bytes plus a small
+fixed overhead, so a line close to the limit, or many short lines, can be cut
+or omitted earlier than their plain total would suggest) and the final rendered
+message including its label. Lines that do not fit are replaced by `[N more
+matched lines omitted]`, and a first line that does not fit is cut and
+marked. The limit is never below 1024 bytes (the configuration floor), enough for
+the framing and an omission marker with ordinary job names; when variable
+framing such as a very long job name does not fit, the monitor sends a bounded
+summary that starts with `+N omitted` instead of the lines. A run keeps only a bounded prefix of its lines in memory (at most
+the delivery limit, or 1 MiB when the limit is disabled, counting a small fixed
+overhead per line) but
+counts every match, so the omitted count is exact and an `ERROR:`/`WARN:` line
+past the retained prefix still sets the label.
+
+| Continuous job (no `--schedule`)                                | Delivered as                                  |
+| --------------------------------------------------------------- | --------------------------------------------- |
+| Contains `error`, `fatal`, `fail`, `permission denied`          | `[FAIL] <name>: matched error pattern` + line |
+| Contains `warn` or `warning`                                    | `[WARN] <name>: matched WARNING` + line       |
+| Contains a whole word `success`, `succeeded`, `complete`, `completed`, `done`, `ok` | Not delivered (logged only)   |
+| Any other matched line                                          | The line, verbatim                            |
+
+A continuous job checks a line for a negated completion word (`not complete`)
+first, then for a level prefix (`ERROR:`, `WARN:`, `INFO:`, optionally after a
+timestamp), then for the words above. Tokens such as `fail=0` are not failures;
+the phrase `0 errors` still contains `error`.
+
+Delivery limits:
+
+- A continuous job delivers the first matching line in each debounce window at
+  once and holds later ones for a trailing summary. A scheduled job has no
+  debounce; its lines are aggregated as above.
+- The `[FAIL]` body for a non-zero exit carries only the last 500 bytes of
+  output, so the message that matters goes last.
+
+## Prompt-Only Reminder
+
+A reminder is a monitor whose command only prints a fixed line. Give the line a
+stable prefix and match exactly that prefix.
+
+```bash
+thrum monitor start --name standup-nudge --to @me \
+  --match '^REMINDER-STANDUP:' --schedule "0 9 * * 1-5" -- \
+  echo "REMINDER-STANDUP: post the status update, then reply to the open review"
+```
+
+- Schedule the reminder; words in its text, including "failures", "error" and
+  "done", then neither relabel nor drop it, and the exit code decides success.
+- Make the body an instruction with the next concrete step; a bare "reminder"
+  carries no action.
+- Add `--notify-on-success` only when a delivered line must be guaranteed for a
+  run that matched nothing.
+- A delivered reminder shows the schedule fired. It does not show that the work
+  moved. Check the work itself (commits, queue, state) before treating the
+  reminder as progress.
+
+## Script Check
+
+A script check runs a bounded, synchronous probe and reports through its exit
+code and one structured line.
+
+```bash
+thrum monitor start --name disk-check --to @me \
+  --match '^CHECK-DISK:' --schedule "*/15 * * * *" -- \
+  bash -c 'u=$(df --output=pcent / | tail -1 | tr -dc 0-9)
+  [ "$u" -lt 90 ] && exit 0
+  echo "CHECK-DISK: root volume at ${u} percent used, free space then rerun df -h /"
+  exit 3'
+```
+
+Rules:
+
+1. Bound every probe with `timeout <secs>`; a hung probe holds the tick.
+2. Exit 0 for healthy and print nothing matching, which keeps the run quiet.
+3. Exit non-zero for a failure; the daemon sends the `[FAIL]` notice with the
+   exit code and output tail.
+4. Print a matching line that names the subject, the observed value and the
+   next action. A generic `OK` or `done` line carries no information.
+5. Use a distinct stable prefix per outcome (`CHECK-DISK:` for a finding,
+   `REMINDER-DISK:` for a nudge) so `--match` selects what must reach the
+   target.
+
+| Outcome  | Script does                              | Target receives                    |
+| -------- | ---------------------------------------- | ---------------------------------- |
+| Quiet    | Exit 0, no matching line                 | Nothing                            |
+| Failure  | Non-zero exit, finding line last         | One `[FAIL] <name>: exit code N` message with the tail and the finding line |
+| Finding  | Exit 0, matching line(s)                 | The line(s), verbatim (labeled only by an `ERROR:`/`FATAL:`/`FAIL:` or `WARN:`/`WARNING:`/`ALERT:` prefix) |
+| Reminder | Exit 0, one stable-prefix instruction    | The line, verbatim                 |
+
+A `--match` that never matches the script's real output delivers nothing and
+raises no error. Test the regex against the exact output before starting.
+
+## Verify By Delivery
+
+Start the monitor with a unique name, `--to` the verifying agent, and a
+one-minute schedule, then read the delivered message back in full.
+
+```bash
+thrum monitor start --name verify-<unique> --to @me --match '^VERIFY-<unique>:' \
+  --schedule "* * * * *" -- echo "VERIFY-<unique>: delivery body check"
+thrum inbox --unread
+thrum message get <message-id>      # the complete delivered body
+thrum monitor logs verify-<unique>  # the matches the daemon recorded
+thrum monitor delete verify-<unique>
+```
+
+Confirm the body carries the prefix, the wording and no unexpected `[FAIL]`
+or `[WARN]` label. Delete the monitor when done; never alter a monitor another
+agent owns.
+
+## Troubleshooting
+
+- Nothing arrived: `thrum monitor show` for state and last exit, `thrum
+  monitor logs` for recorded matches. No recorded match means the regex did not
+  match, or (continuous job) the line was completion-classified and suppressed;
+  run the command by hand and compare its output with the regex.
+- Message labeled `[FAIL]` unexpectedly: the job exited non-zero, the line starts
+  with `ERROR:`/`FATAL:`/`FAIL:`, or (continuous job) the line contains a fail or
+  error substring.
+- Name already in use: a stopped record holds it. `thrum monitor delete` it.

package/assets/skills/using-the-queue/SKILL.md

@@ -191,7 +191,7 @@ so this wrapper is defense-in-depth, not load-bearing on its own.
   non-peercred transport (browser/WS, unit tests) - but that is a general,
   already-documented property of the RPC layer (identity trust depends on
   transport), not something unique to `state.set`, and it is explicitly out
-  of scope per `docs/security_model/master.md` §1.5: "Thrum does not attempt
+  of scope per the project's security model: "Thrum does not attempt
   to prevent agent identity forgery" is an owner ruling, stated as
   [INTENDED] and permanent, not tracked as debt.
 
@@ -204,8 +204,7 @@ shapes, chosen by domain, not an oversight.
 
 Non-goal: fail-closed reject-symmetry for `state.set` (mirroring queue's
 `RejectIdentityKeysHandler`) is a possible future non-security hardening
-preference, not built here - out of scope per `docs/security_model/master.md`
-§1.5.
+preference, not built here - out of scope per the project's security model.
 
 ## Common Mistakes
 

package/assets/skills/using-thrum-state/SKILL.md

@@ -42,8 +42,8 @@ time** — writing a fleet row without a fresh by-effect check, even to
 ## Reconcile, don't just read
 
 - **Agent-local** (all roles): check at session start
-  (`thrum state list`), update as you go. Carried-over state is NOT
-  auto-injected into prime — you must ask.
+  (`thrum state list`), update as you go. Prime injects only a capped digest
+  of agent-local state; `thrum state list` shows all.
 - **Fleet** (coordinators write; everyone reads): before citing a fleet
   fact in a decision, check `as_of`/`method`. Past the kind's threshold
   (`thrum state describe <kind>`)? Re-verify by effect before acting, or
@@ -73,7 +73,7 @@ yourself.
 
 ## Field Mutability Matrix
 
-`Entry` (`internal/state/types.go`) has five mutability classes, not one
+The state `Entry` type has five mutability classes, not one
 uniform "immutable field" guard:
 
 - **immutable-identity** — part of the `(Kind, Scope)` addressing key, or

package/assets/skills/verify-against-plan/SKILL.md

@@ -104,7 +104,7 @@ clear error — do not proceed with partial inputs.
    Regex: `^\*\*Authored-against:\*\* \`([0-9a-f]+)\` target: \`([^\`]+)\``
    (sha → capture group 1, merge_target → capture group 2)
 
-   (Canonical stamp definition: `claude-plugin/commands/_stamp-protocol.md`. The
+   (Canonical stamp definition: the /thrum:stamp-protocol skill. The
    stamp follows the same literal `grep -F` / fixed-field-order / case-sensitive /
    ASCII-only convention as the `THRUM-REVIEW` marker — see
    `coordinator-running-brainstorm-cycles` skill § "Footer → commit → stamp".)
@@ -158,7 +158,7 @@ clear error — do not proceed with partial inputs.
    present" outcome above, since this check only needs the stamp's
    `<sha>`/`<merge_target>`, not the plan's cited-files list. Run the
    ordered, short-circuiting two-check sequence defined canonically in
-   `_stamp-protocol.md` § "Read-time provenance re-derivation" (SHA-resolves
+   `stamp-protocol.md` § "Read-time provenance re-derivation" (SHA-resolves
    first, then merge-status) against the stamp's `<sha>`/`<merge_target>` —
    the exact commands live there as the single source of truth; this section
    states outcomes and severity only:

package/dist/hooks/block-sync-cd.js

@@ -29,7 +29,7 @@ const SYNC = String.raw `\.git/thrum-sync/a-sync`;
 // Command-position anchor: line start or immediately after a shell separator
 // (;, &&, ||), then optional whitespace. This matches `cd`/`git` only when they
 // are the actual command — NOT when those words appear inside a quoted argument
-// preceded by a bare space (the D5 false-positive: `bd remember "... cd
+// preceded by a bare space (the quoted-argument false-positive: `bd remember "... cd
 // .git/thrum-sync/a-sync ..."` must NOT be denied). Match op-shape, not the mere
 // presence of the path string.
 const CMDPOS = String.raw `(^|;|&&|\|\|)\s*`;

package/dist/hooks/block-sync-cd.test.js

@@ -31,7 +31,7 @@ const ALLOW = [
     ["git -C a-sync push", `git -C ${ASYNC} push`],
     ["git -C a-sync log (not branch-changing)", `git -C ${ASYNC} log --oneline`],
     ["ls the path", `ls ${ASYNC}/`],
-    // D5 false-positive guard: cd inside a quoted argument (bare space before it),
+    // quoted-argument false-positive guard: cd inside a quoted argument (bare space before it),
     // not at command position -> must be ALLOWED.
     ["quoted cd inside bd remember", `bd remember "note: do not cd ${ASYNC} directly"`],
 ];

package/dist/installer-assets.test.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/installer-assets.test.js

@@ -0,0 +1,41 @@
+// Tests for installAssets skills/commands staging (o4jgf MINOR 13):
+// expected content lands on first install, and the version gate makes a
+// second install a no-op. Offline/deterministic: temp XDG_CONFIG_HOME,
+// stub ctx, real asset tree, never the real $HOME or network.
+//
+// Run: npm test  (builds, then `node --test dist`)
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import fs from "fs";
+import os from "os";
+import path from "path";
+import { getConfigDir, installAssets } from "./installer.js";
+function stubCtx() {
+    return { client: { app: { log: async () => { } } } };
+}
+test("installAssets stages skills and commands; version gate skips reinstall", async () => {
+    const tmp = fs.mkdtempSync(path.join(os.tmpdir(), "thrum-oc-install-"));
+    const prevXdg = process.env.XDG_CONFIG_HOME;
+    process.env.XDG_CONFIG_HOME = tmp;
+    try {
+        await installAssets(stubCtx());
+        const cfg = path.join(tmp, "opencode");
+        assert.equal(getConfigDir(), cfg);
+        // protocol skills ride the wholesale skills copy (o4jgf item 5)
+        const skillFile = path.join(cfg, "skills", "snapshot-protocol", "SKILL.md");
+        assert.ok(fs.existsSync(skillFile));
+        assert.ok(fs.existsSync(path.join(cfg, "commands", "thrum-sleep.md")));
+        const mtimeBefore = fs.statSync(skillFile).mtimeMs;
+        await installAssets(stubCtx());
+        assert.equal(fs.statSync(skillFile).mtimeMs, mtimeBefore);
+    }
+    finally {
+        if (prevXdg === undefined) {
+            delete process.env.XDG_CONFIG_HOME;
+        }
+        else {
+            process.env.XDG_CONFIG_HOME = prevXdg;
+        }
+        fs.rmSync(tmp, { recursive: true, force: true });
+    }
+});

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-thrum-pro",
-  "version": "0.1.6",
+  "version": "0.1.8",
   "description": "Thrum multi-agent coordination plugin for Open Code",
   "type": "module",
   "main": "./dist/index.js",

package/assets/commands/thrum-_compact-runtime-commands.md

@@ -1,61 +0,0 @@
----
-description:
-  Per-runtime compact-equivalent command table consumed by compact.md,
-  compact-extended.md, and scripts/sync-skills.sh. Not user-invocable
-  directly.
----
-
-# Per-Runtime Compact Command Table (shared partial)
-
-Consumers: `claude-plugin/commands/compact.md`, `compact-extended.md`
-(reference this table for the command each runtime's synced copy sends), and
-`scripts/sync-skills.sh`'s `compact_command_for_runtime()` (the executable
-mirror of this table — keep the two in lockstep; a row added/changed here
-without a matching case in that function is a defect at review, not a style
-nit).
-
-This is the canonical, cited source of truth for what "the compact command"
-means on each runtime thrum drives. Do NOT invent a command for a runtime not
-listed here or not sourced — an unverified guess sent to a runtime's pane is
-worse than no compaction at all (it either no-ops or does something
-unintended). A runtime found to have no equivalent is recorded as such, not
-silently omitted.
-
-| Runtime      | Compact command                 | Source                                                                                                      | Confidence                    |
-| ------------ | -------------------------------- | -------------------------------------------------------------------------------------------------------------- | ------------------------------ |
-| `claude`     | `/compact`                       | Claude Code built-in slash command (already established in this project).                                       | Verified — first-party.        |
-| `codex`      | `/compact`                       | OpenAI Codex CLI context-compaction architecture (server-side `POST /v1/responses/compact`, manual trigger `/compact`). | Verified — corroborated by two independent technical write-ups; not fetched from `codex --help` directly. |
-| `opencode`   | `/compact` (alias `/summarize`)  | opencode.ai official docs, keybinds reference — `session_compact` action, default slash command `/compact`.     | Verified from official docs. **Caveat:** a differently-named community fork lacks this command — confirm against the specific `opencode` binary before relying on it blindly. |
-| `cursor`     | `/summarize` (alias `/compress`) | cursor.com CLI reference, slash-commands page.                                                                   | Verified from official docs. **Differs from Claude's `/compact`** — this is the one runtime where the sent text must actually change. `/clear` (aliases `/new`, `/new-chat`) is a separate full-reset command, not compaction — do not confuse the two. |
-| `copilot`    | `/compact`                       | docs.github.com, "Managing context in GitHub Copilot CLI".                                                       | Verified from official docs. **Not currently shippable**: `copilot-plugin/` has no skills/commands-loading mechanism at all (pre-existing, documented in `scripts/sync-skills.sh`'s header) — this row exists for completeness/future readiness, not because the skill ships there today. Coverage tracked as a build-vs-accept scope call, owner-owned. |
-| `muse`       | **NONE FOUND**                   | musecodes.io official docs — documented commands are `/plan`, `/grill`, `/goal`, `/workflows`, `/model`, `/effort`, `Esc Esc` (rewind), `muse replay`. No manual compact/summarize trigger is documented; marketing copy describing context "compaction" refers to an automatic/internal mechanism only, not a user-invocable command. | Verified absence, not an inferred gap. Per E9 (owner-ruled), muse falls to the `restart-extended` exception — it does not receive compact.md/compact-extended.md. |
-| `gemini`     | **UNVERIFIED**                   | Not researched — no plugin tree exists for this runtime, and it was never included in this table's original research pass. | **Not a confirmed negative.** Go-side `internal/runtime.RuntimePreset` exists for this runtime with `CompactCommand` deliberately left empty (falls back to `/thrum:restart-extended`, never invented). This research is not yet done — do not research here; treat future work on this row as owned elsewhere. |
-| `kiro-cli`   | **UNVERIFIED**                   | Same as `gemini` — not researched, no plugin tree.                                                              | Same as `gemini` — empty `CompactCommand`, safe fallback, research pending. |
-| `amp`        | **UNVERIFIED**                   | Same as `gemini` — not researched, no plugin tree.                                                              | Same as `gemini` — empty `CompactCommand`, safe fallback, research pending. |
-| `shell`      | **UNVERIFIED**                   | Same as `gemini` — not researched, no plugin tree.                                                              | Same as `gemini` — empty `CompactCommand`, safe fallback, research pending. |
-
-## Notes
-
-- `codex` and `opencode` resolve to the same literal string Claude uses
-  (`/compact`), so their synced copies are a functional no-op substitution —
-  still routed through the same mechanism for consistency and so a future
-  table change (e.g. if `opencode`'s fork situation resolves differently)
-  propagates without a second code path.
-- `cursor` is the one runtime whose synced copy's sent command differs from
-  Claude's and must be verified after every sync run (`grep` step in
-  `scripts/sync-skills.sh`'s `compact_command_for_runtime` block).
-- `muse` and `copilot` are both absent from compact/compact-extended's sync
-  targets today, for two *different* reasons — `muse` because no native
-  command exists to send, `copilot` because the plugin has no delivery
-  mechanism at all. Neither is a silent drop: both are recorded here and
-  reported in the completion report for this table's original research pass.
-- `gemini`/`kiro-cli`/`amp`/`shell` are recorded as **UNVERIFIED**, not
-  merged into the `muse`/`copilot` "no equivalent" rows above — those two are
-  confirmed negatives (verified by reading official docs); the four
-  UNVERIFIED rows are an absence of research, not an absence of a command.
-  `scripts/sync-skills.sh`'s `compact_command_for_runtime()` already returns
-  `""` for any of these four via its `*` default case, so the executable
-  mirror and this table already agree — no code change is needed to keep
-  them in lockstep, only this documentation. See also
-  `dev-docs/reference/compaction-lifecycle-attach-points.md` for the same
-  four runtimes' hook-attach-point status.

package/assets/commands/thrum-_generator-idempotency-protocol.md

@@ -1,15 +0,0 @@
----
-description:
-  Shared generator-skill idempotency invariant consumed by config/doc
-  generator skills. Not user-invocable directly.
----
-
-# Generator Idempotency Protocol (shared partial)
-
-Consumers: run `grep -rl _generator-idempotency-protocol claude-plugin/skills/`
-for the current set — do NOT hardcode it here. A list of consumers inside the
-consumed file is a second copy of a git-answerable fact and rots the moment a
-skill is added or dropped.
-
-The modes are idempotent — running the skill repeatedly on a stable project
-should produce no file changes after the first run.

package/assets/commands/thrum-_project-rules-protocol.md

@@ -1,18 +0,0 @@
----
-description:
-  Shared project-specific-rules protocol consumed by role skills. Not
-  user-invocable directly.
----
-
-# Project-Specific Rules Protocol (shared partial)
-
-Consumers: run `grep -rl _project-rules-protocol claude-plugin/skills/` for the
-current set — do NOT hardcode it here. A list of consumers inside the consumed
-file is a second copy of a git-answerable fact and rots the moment a skill is
-added or dropped.
-
-Project-local rules of kind `agent_rule` at `--scope role` were loaded at
-session start by your preamble (see your role template's Memory model block).
-If a project-local rule conflicts with a universal rule above, the
-project-local rule wins; surface the conflict in your reply so the user can
-decide whether to graduate or remove the override.

package/assets/commands/thrum-_verify-before-write-protocol.md

@@ -1,27 +0,0 @@
----
-description:
-  Shared "Verify before you write" invariant consumed by state-writing
-  skills. Not user-invocable directly.
----
-
-# Verify Before You Write Protocol (shared partial)
-
-Consumers: run `grep -rl _verify-before-write-protocol claude-plugin/skills/`
-for the current set — do NOT hardcode it here. A list of consumers inside the
-consumed file is a second copy of a git-answerable fact and rots the moment a
-skill is added or dropped.
-
-A written fact is TRUE at the moment it's recorded and can silently become
-FALSE later — the reader can't tell, because a note doesn't present itself as
-a time-bound claim. Before writing anything:
-
-- Only write what you've verified against current state — not what you
-  remember, assume, or were told once.
-- A note recording an UNEXPLAINED artifact must carry the unexplained-ness
-  forward — "not mine, cause unknown, nobody has traced this" — rather than
-  resolving it to a disposition like "ignore it." The note isn't wrong to cope
-  with noise you can't act on; the defect is closing the question when
-  nothing is actually known. "Ignore it" is unfalsifiable by construction —
-  an instruction to not look can't be caught by looking, because diligence is
-  exactly what it switches off — and it can silently train every future
-  session to stop looking at the one visible symptom of a live bug.