@assuredloop/orca-bot-kit 0.18.0 → 0.20.0

package/skills/obk-researching/NOTICE.md

@@ -43,6 +43,9 @@ thanks. Each licence below was read from the file named beside it.
   - `why/SKILL.md` adds coverage rather than minimalism, documenting the null
     instead of skipping the search, and the high bar for skipping a source:
     provably irrelevant rather than probably irrelevant.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`addyosmani/agent-skills`, `skills/source-driven-development`**: MIT,
   `addyosmani_agent-skills/LICENSE`, "Copyright (c) 2025 Addy Osmani". The
   source hierarchy and what sits outside it: model-written summaries and your
@@ -60,6 +63,9 @@ thanks. Each licence below was read from the file named beside it.
   could not find documentation. And the rule this skill takes whole, that
   hedging is the worst of the three options: either verify and cite, or mark it
   unverified, because a disclaimer in a subordinate clause reads as confidence.
+  Revision: addyosmani/agent-skills@dc27a9c2e13721158157632de61b4106c6c2a2a1
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`garrytan/gstack`, `ETHOS.md`**: MIT, `garrytan_gstack/LICENSE`,
   "Copyright (c) 2026 Garry Tan". The three layers of what you find and how
   much weight each bears: the settled and well-trodden, where the risk is
@@ -71,6 +77,9 @@ thanks. Each licence below was read from the file named beside it.
   look things up by general category rather than by the private thing you are
   working on, and strip names, addresses, paths and anything that looks like a
   secret from a query before it leaves the machine.
+  Revision: garrytan/gstack@a6b3a57512ca6d5c6aa5b68f74f736195021f96e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`openai/skills`, `skills/.curated/notion-research-documentation`**: MIT,
   that skill's own `LICENSE.txt`, "Copyright 2025 Notion Labs, Inc." The search
   strategy, which is the only material of its kind in the sources: broad to
@@ -83,30 +92,42 @@ thanks. Each licence below was read from the file named beside it.
   citing every sentence, put the citation beside what it supports, mark a
   quotation as a quotation, keep a sources section that includes what held
   nothing, and flag a superseded source where it stands.
+  Revision: openai/skills@49f948faa9258a0c61caceaf225e179651397431
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`mattpocock/skills`, `skills/engineering/research`**: MIT,
   `mattpocock_skills/LICENSE`, "Copyright (c) 2026 Matt Pocock". Twelve lines,
   one of which the research pack singled out and this skill is built around:
   follow every claim back to the source that owns it, and go to primary
   material rather than a secondary write-up of it.
+  Revision: mattpocock/skills@c55ee46073ed923f86ce59a5eb3b6d895095d1b7
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Cloudflare's security-audit skill**: MIT,
   `cloudflare_security-audit-skill/LICENSE`, "Copyright (c) 2025-2026
   Cloudflare, Inc." Coverage honesty: never imply that one pass exhausts the
   subject, and a scoped piece of work presents itself as partial rather than
   letting silence read as "the rest is fine".
+  Revision:
+  cloudflare/security-audit-skill@c1c8a8c1471069fb0e188eeaff69b8e8db6564a8
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 
 Two things come from the research pack rather than from a repository, and are
 marked here because the difference matters:
 
-- The evidence-label pair `(verified: <command>)` and `(inferred: did not
-  run)`, which `source-book-2.md:139` calls the single best sentence in its
-  whole survey, is quoted there from **tw93/Waza**'s `rules/anti-patterns.md`
+- **tw93/Waza**, `rules/anti-patterns.md`: the evidence-label pair `(verified:
+  <command>)` and `(inferred: did not run)`, which `source-book-2.md:139` calls
+  the single best sentence in its whole survey, is quoted there from it
   (recorded as MIT in the same book's source table). Waza is not among the
   clones in the research pack, so this is taken from the book's verbatim quote
   rather than from the repository. The label's checkable form is kept as the
   source has it, because being able to audit the label is the whole of its
-  value; the prose around it is ours. The source applies `inferred` to
-  reasoning from code, so this skill keeps it for an inference and asks for
-  `not checked` where the claim is somebody else's unchecked account.
+  value; the prose around it is ours. The source applies `inferred` to reasoning
+  from code, so this skill keeps it for an inference and asks for `not checked`
+  where the claim is somebody else's unchecked account.
+  Revision: tw93/Waza@59323dee82b04fa8b9ad97a8ee503ca8aee7eb3c (as recorded
+  in the research pack's source-book-2.md, read 2026-09-19)
 - The pack's own reports label each claim by where it came from and whether it
   was checked, and keep a section of gaps and cautions at the end. That habit,
   rather than any source, is why this skill treats a claim's support and the

package/skills/obk-reviewing/NOTICE.md

@@ -16,6 +16,9 @@ noted, with thanks:
   has no caller, premature abstraction, "I would have done it differently",
   about five items, and showing what was set aside. Its `poteto-mode`
   bugbot-triage reference gave fix, dismiss or ask, and "when in doubt, ask".
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **obra/superpowers**, `requesting-code-review`, `receiving-code-review` and
   `subagent-driven-development/task-reviewer-prompt.md` (the last for bounded
   reading, "declined to judge", the read-only rule and one focused test only
@@ -27,6 +30,9 @@ noted, with thanks:
   pattern: read, restate, verify, evaluate, respond, implement, with the stop
   on an unclear item, the check for who calls it, the order of fixes, and
   correcting your own pushback without a speech.
+  Revision: obra/superpowers@5bf4e78011075bcfc0dc295f0724994cd123ee71
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **mattpocock/skills**, `code-review`: the smell baseline in full, with its
   own guards: every entry a labelled judgement call, the repo's documented
   standard overriding it, and anything tooling enforces skipped. Also pinning
@@ -34,17 +40,26 @@ noted, with thanks:
   missing, unasked-for and misunderstood, quoting the rule for a standards
   breach, and the two axes staying separate so neither hides the other. The
   smells are Fowler's, from *Refactoring* chapter 3.
+  Revision: mattpocock/skills@c55ee46073ed923f86ce59a5eb3b6d895095d1b7
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Cursor thermos**, with `thermo-nuclear-review`: scope held to what the
   change touches, not spending the author's time on a breakage the change
   intends, what over-reporting costs you,
   reading the change before the discussion, and never presenting a finding with
   the research unfinished when the answer was there to be read.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **addyosmani/agent-skills**: passing the artefact and the contract without
   the conclusion, the one structural problem outranking ten small ones, and,
   from `doubt-driven-development`, sorting findings into misread, valid,
   trade-off and noise in that order, with the brief fixed first for a misread.
   Its `code-review-and-quality`: not softening a real issue, which pstack's
   `code-quality-review` says too.
+  Revision: addyosmani/agent-skills@dc27a9c2e13721158157632de61b4106c6c2a2a1
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Anthropic's built-in review**, as behaviour observed rather than text
   taken: the angles worth separating, naming the behaviour a deleted line held
   up, following a change out to its callers, confirmed against plausible
@@ -53,6 +68,10 @@ noted, with thanks:
   bug states its trigger, not collapsing finding into judging,
   correctness outranking cleanup, and saying when a review was less than it was
   meant to be.
+  Revision: none (Claude Code's built-in review, its behaviour observed rather
+  than a text read)
 - **ECC's reviewer prompt**, through the research pack: the four questions
   before a finding, a defensible severity, zero findings being expected,
   consolidating repeats, and the list of findings that are usually wrong.
+  Revision: affaan-m/ECC@07756cee15788a54506031462794ad645719b028 (as recorded
+  in the research pack's source-book-2.md, read 2026-09-19)

package/skills/obk-tdd/NOTICE.md

@@ -14,6 +14,9 @@ thanks:
   `to-spec`: the existing seam preferred, the highest one, and the fewer the
   better. Its `diagnosing-bugs`: the correct seam for a bug test, and no
   correct seam being the finding.
+  Revision: mattpocock/skills@c55ee46073ed923f86ce59a5eb3b6d895095d1b7
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **obra/superpowers**, `test-driven-development` and its `writing-good-tests`:
   naming the break a test catches, deriving the expected value by hand, change
   detectors, behaviour rather than text, your contract rather than the
@@ -21,16 +24,25 @@ thanks:
   the mutation classes. Its `verification-before-completion`: the
   revert-the-fix proof. Its `writing-plans`: a requirement's silence not being
   permission, and the few uncovered input classes most likely to bite.
+  Revision: obra/superpowers@5bf4e78011075bcfc0dc295f0724994cd123ee71
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Cursor pstack**, `tdd` and `principle-test-behavior-not-implementation`:
   the five shapes that observe no behaviour and the fix for each (asserting
   what a stand-in received rather than that it was called, and the relation
   across rows of data that is kept), "prefer no
   new test over a bad test", the honest exit when a test is impractical, and
   the report that names the failing-before and passing-after runs.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **addyosmani/agent-skills**, `test-driven-development` and
   `constraint-driven-development`: finding out how the project tests before
   writing anything, repetition being no fault in a test, a subagent for the
   reproduction test, and the cheap roads to green.
+  Revision: addyosmani/agent-skills@dc27a9c2e13721158157632de61b4106c6c2a2a1
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **citypaul/.dotfiles**, `tdd` and `mutation-testing` with its
   `mutator-rules`: the mutation loop, survivor triage into killed, equivalent
   or named and deferred, the equivalence question, the high-value logic worth
@@ -38,15 +50,34 @@ thanks:
   mixed true and false, no identity values), the tool-run mechanics in
   `mutation-tools.md`, keeping the harness out of the inner loop, triangulating
   after a fake, and refusing to manufacture a red.
+  Revision: citypaul/.dotfiles@a109f9972bb46671c624fc05752031523e1cf6fc
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Kent Beck's own rules file**: one test at a time, the smallest code that
   passes, structure and behaviour kept apart, and the two-level test for a
   defect.
+  Revision: KentBeck/BPlusTree3@ca80e4d85a99cd0af2effe717f709d43e80403bc
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **nizos/tdd-guard**: the ladder to a clean red.
+  Revision: nizos/tdd-guard@2579ec1823fac5f4afb73be678d9c500b19885ac (as
+  recorded in the research pack's source-book-2.md, read 2026-09-19)
 
-Ideas paraphrased, with no text taken: Trail of Bits' mutation-testing skill
-(CC BY-SA 4.0) on equivalent mutants, Anthropic's Claude Code documentation on
-separate test authorship, alexop.dev on why one context cannot hold both
-halves, and the published work on mutation testing at scale.
+Ideas paraphrased, with no text taken:
+
+- **Trail of Bits' mutation-testing skill**, in `trailofbits/skills` (CC BY-SA
+  4.0), on equivalent mutants.
+  Revision: trailofbits/skills@123037ec8aed26f0d86327cc39137ee5043e5deb (as
+  recorded in the research pack's source-book-2.md, read 2026-09-19)
+- **Anthropic's Claude Code documentation**, "Claude Code: Best practices", on
+  separate test authorship.
+  Read: 2026-09-19 (read for the research pack's source-book-1.md, of that date)
+- **alexop.dev**, "A Claude Code TDD Skill: Forcing Red-Green-Refactor", on why
+  one context cannot hold both halves.
+  Read: 2026-09-19 (read for the research pack's source-book-1.md, of that date)
+- **The published work on mutation testing at scale**, Petrović and others,
+  "Practical Mutation Testing at Scale" (arXiv 2102.11378).
+  Read: 2026-09-19 (read for the research pack's source-book-1.md, of that date)
 
 Our own, with no source behind them: the order to break things in, the red
 from an archived baseline for behaviour that already existed, checking that an

package/skills/obk-teach/NOTICE.md

@@ -45,6 +45,9 @@ thanks:
   print, and the reply being the explanation itself rather than a report about
   it). Its worked density example is not carried; the rules it illustrates
   are.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 
 Made generic, which is what the owner asked for. The original is built on top
 of two other skills it invokes by name, and a kit skill carries what it needs

package/skills/obk-why/NOTICE.md

@@ -37,6 +37,9 @@ The skill `obk-why` was consolidated for this kit from this, MIT, with thanks:
   including one line per source consulted covering the empty and skipped ones;
   and turning the findings into a preserve, change, avoid and risk constraint
   set when the question precedes a change.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - The same skill's `references/sources/code-archaeology.md`. Its pitfalls: the
   squash merge that flattens a branch's steps, the commit message that calls a
   behaviour change a small refactor so the diff has to be read instead, the

package/skills/obk-writing/NOTICE.md

@@ -30,6 +30,9 @@ Each licence below was read from the file named beside it.
   read machine-written when every sentence is clipped to the same length; its
   heading rule, that a heading carries the point rather than the topic; its
   list rules; and the instruction to call each thing by one name everywhere.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **Cursor `plugins`, `pstack/skills/unslop`**: same licence. Two of its rules
   are load-bearing here. Say what it does rather than how it feels, with its
   test: ask what the sentence tells the reader to do or know, restate it as a
@@ -44,6 +47,9 @@ Each licence below was read from the file named beside it.
   named above are kept in their positive form, not every rule in the catalogue,
   and the word list is left where it is, as something to review against rather
   than to load.
+  Revision: cursor/plugins@6ed0f7a9504f577d7529064103cecce9be7dfc5e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`citypaul/.dotfiles`, `claude/.claude/skills/technical-writing`**: MIT,
   that skill's own nested `LICENSE`, "Copyright (c) 2025 Adam Bulmer", which
   governs its directory rather than the repository root's MIT licence in
@@ -63,6 +69,9 @@ Each licence below was read from the file named beside it.
   leads with the decision requested. And from `resources/formatting.md`, bold
   for the one phrase a skimmer must not miss, and a numbered list claiming that
   order matters.
+  Revision: citypaul/.dotfiles@a109f9972bb46671c624fc05752031523e1cf6fc
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`mattpocock/skills`, `skills/in-progress/writing-shape`**: MIT,
   `mattpocock_skills/LICENSE`, "Copyright (c) 2026 Matt Pocock". The grounding
   idea, which nothing else in the sources has: every concept a block leans on
@@ -73,6 +82,9 @@ Each licence below was read from the file named beside it.
   drowns the opening. Its format arguments are also taken: prose carries an
   argument and lists carry parallel items, a table where the same shape repeats
   three times or more, and quoting where the original wording is the point.
+  Revision: mattpocock/skills@c55ee46073ed923f86ce59a5eb3b6d895095d1b7
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`anthropics/skills`, `skills/internal-comms`**: Apache 2.0, that skill's
   own `LICENSE.txt`, "Copyright 2026 Anthropic, PBC." The only source here that
   is explicitly about audience, platform and register for non-engineering
@@ -83,11 +95,17 @@ Each licence below was read from the file named beside it.
   read is a constraint on the writing rather than a detail: something meant to
   be read in under a minute by people with some but not much context is a
   different piece from the same facts written to be landed on.
+  Revision: anthropics/skills@34040c9c568585f6929bedeaad110ad08f079624
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`garrytan/gstack`, `document-generate/SKILL.md`**: MIT,
   `garrytan_gstack/LICENSE`, "Copyright (c) 2026 Garry Tan". Its voice section:
   lead with the point, be concrete, name the real thing and the real number.
   Its rule to gloss a piece of jargon on first use even where the user
   introduced the term.
+  Revision: garrytan/gstack@a6b3a57512ca6d5c6aa5b68f74f736195021f96e
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 - **`addyosmani/agent-skills`, `skills/doubt-driven-development`** and
   **`citypaul/.dotfiles`, `claude/.claude/skills/double-check`**: MIT,
   `addyosmani_agent-skills/LICENSE` ("Copyright (c) 2025 Addy Osmani") and
@@ -99,6 +117,12 @@ Each licence below was read from the file named beside it.
   than deferring, since a fresh reader can be wrong for want of context; and
   stop when a pass finds only small or known things, bounded at about three
   passes, with a piece still failing then reported as not ready.
+  Revision: addyosmani/agent-skills@dc27a9c2e13721158157632de61b4106c6c2a2a1
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
+  Revision: citypaul/.dotfiles@a109f9972bb46671c624fc05752031523e1cf6fc
+  (reconstructed: the research pack's 2026-09-20 clone the skills were built
+  from; the revision actually read was not recorded)
 
 **Left out on a licence.** `anthropics/skills`' `doc-coauthoring` has the best
 statement of reader testing in the corpus, but its directory holds no licence

package/src/cli.js

@@ -28,7 +28,7 @@ import { readRoster } from './roster.js';
 import { buildAgents, buildRules, CODEX_CAP } from './rules.js';
 import { addSkill, buildSkills, linkSkills, removeSkill } from './skills.js';
 import { addSource, fetchSources } from './sources.js';
-import { makeTemp, retireTemp } from './temp.js';
+import { makeTemp, retireTemp, trustHooks } from './temp.js';
 import { readUsage } from './usage.js';
 import { BOT_FATHER, bringUp, ownMailbox } from './up.js';
 
@@ -99,18 +99,25 @@ Usage:
   obk temp make --bots <path> --name <session>
                 (--prompt <text> | --prompt-file <path>) [--harness claude|codex]
                 [--model <m>] [--effort <e>] [--context <c>]
-                [--approval ${APPROVALS.join('|')}]
+                [--approval ${APPROVALS.join('|')}] [--extra-arg=<arg>]...
                             Run in a long-lived session's own tab: make a
                             temporary session of that session's bot for a piece
                             of work, and bring it up. It takes your harness,
                             model, effort, context and approval unless you say
-                            otherwise, works in work/<session>, and has the task
-                            as its start prompt. The book records it as
-                            temporary, made by you.
+                            otherwise; on another harness than yours it takes
+                            only your approval. It works in work/<session>, and
+                            has the task as its start prompt. The book records
+                            it as temporary, made by you.
   obk temp retire --bots <path> --name <session>
                             Run in the maker's own tab: retire a temporary
                             session it made, as obk retire does. It refuses a
                             long-lived session, or one another session made.
+  obk temp trust-hooks --bots <path> --name <session>
+                            Run in the maker's own tab: answer the hooks review
+                            of a Codex temporary session it made with "Trust
+                            all and continue", and check the review went. It
+                            refuses anything else on that screen, and types
+                            nothing then.
   obk rules build --bots <path> [--bot <bot>]
                             Build every bot's AGENTS.md from its charter and
                             the rule units it carries, or just the one you
@@ -190,7 +197,8 @@ Usage:
                             with its settings, its tab and the conversation it
                             is in. It reads your files and reports them as they
                             stand; what to make of them is yours.
-  obk groom --bots <path> [--on [--at <HH:MM>] | --at <HH:MM> | --off | --now | --compact]
+  obk groom --bots <path> [--on [--at <HH:MM>] [--run-on codex [--model <m>] [--effort <e>] [--extra-arg=<arg>]...]
+                | --at <HH:MM> | --off | --now | --compact]
                             Say what the daily grooming is: Bot Father's session
                             grooming, and the job scheduled in it on Claude
                             Code's own scheduler. Add that session like any
@@ -201,19 +209,23 @@ Usage:
                             day, so run it by hand once and read it first. --at
                             moves it, --off unschedules it, and --compact
                             compacts its conversation between runs. It fires
-                            only while its tab is up in Orca.
+                            only while its tab is up in Orca. --run-on codex
+                            makes each run a temporary Codex session of the
+                            grooming session's, launched with --model, --effort
+                            and --extra-arg, which reports back by the kit's
+                            mail and is retired.
   obk usage --bots <path> [--bot <bot>] [--session <name>] [--since <time>] [--until <time>]
                             Say what your sessions have used: the conversations
                             each one had, their calls and tokens (their
-                            subagents' included, and how many were theirs), the
-                            models and efforts they ran at, and how often they
-                            were compacted. --since counts the calls made from
-                            that moment on, and --until the calls made before
-                            that one: a daily run asks from the last run's end
-                            up to its own, and the next starts where it stopped,
-                            so no call is counted twice. It counts tokens and
-                            never money: what a token costs is looked up live by
-                            whoever is asking.
+                            subagents' and Codex's auto-reviews included, and
+                            how many were whose), the models and efforts they
+                            ran at, and how often they were compacted. --since
+                            counts the calls made from that moment on, and
+                            --until the calls made before that one: a daily run
+                            asks from the last run's end up to its own, and the
+                            next starts where it stopped, so no call is counted
+                            twice. It counts tokens and never money: what a
+                            token costs is looked up live by whoever is asking.
   obk session record --bots <path> --bot <bot>
                             For the kit's own hook, not for typing: it reads
                             what the harness says about a session starting on
@@ -260,6 +272,7 @@ const COMMANDS = {
   'session mailbox': ['bots', 'bot', 'session'],
   'temp make': ['bots', 'name'],
   'temp retire': ['bots', 'name'],
+  'temp trust-hooks': ['bots', 'name'],
 };
 
 /** What each flag is for, in the sentence a caller reads when it is missing. */
@@ -333,6 +346,7 @@ async function run(argv) {
       disallow: { type: 'string', multiple: true },
       ...Object.fromEntries(SETTINGS.map(([flag]) => [flag, { type: 'string' }])),
       'extra-arg': { type: 'string', multiple: true },
+      'run-on': { type: 'string' },
       json: { type: 'boolean' },
       help: { type: 'boolean', short: 'h' },
       version: { type: 'boolean' },
@@ -601,6 +615,7 @@ const commands = {
       if (values[flag] !== undefined) given[key] = values[flag];
     }
     if (values.context !== undefined) given.context = asNumberOrText(values.context);
+    if (values['extra-arg'] !== undefined) given.extra_args = values['extra-arg'];
     const made = await makeTemp(bots, { tab, ...given });
     const { tabs, rules, skills, permissions, paused, projects } = made.up;
     const answer = { bots, bot: made.bot, session: made.session, maker: made.maker, settings: made.settings, created: [], completed: [], rules, skills, permissions, tabs, paused, projects };
@@ -625,6 +640,16 @@ const commands = {
     };
   },
 
+  async 'temp trust-hooks'(bots, values) {
+    const tab = callerTab(bots, true);
+    refuseWhenOrcaIsDown();
+    const trusted = await trustHooks(bots, { tab, name: values.name });
+    return {
+      answer: { bots, ...trusted },
+      lines: [`trusted    ${trusted.bot} ${trusted.session}'s hooks, a temporary session of ${trusted.maker}'s: chose "Trust all and continue" on its hooks review, and the review has gone`],
+    };
+  },
+
   'bot create'(bots, values) {
     const made = createBot(bots, { name: values.name, harness: values.harness, charter: values.charter });
     // The bot's AGENTS.md is the rules build's, here as everywhere else, so
@@ -821,7 +846,16 @@ const commands = {
     }
     // --at on its own moves grooming that is on to another time.
     const ask = asks[0] ?? (values.at === undefined ? undefined : 'move');
-    const groom = grooming(bots, { at: values.at, ask });
+    // What each run is launched with when it runs on Codex (#238): given only
+    // with --run-on, and refused by grooming() when it is not.
+    const given = ['run-on', 'model', 'effort', 'extra-arg'].some((flag) => values[flag] !== undefined);
+    const run = !given ? undefined : {
+      harness: values['run-on'],
+      ...(values.model === undefined ? {} : { model: values.model }),
+      ...(values.effort === undefined ? {} : { effort: values.effort }),
+      ...(values['extra-arg'] === undefined ? {} : { extra_args: values['extra-arg'] }),
+    };
+    const groom = grooming(bots, { at: values.at, ask, run });
     return { answer: { bots, groom }, lines: groomLines(groom, bots) };
   },
 
@@ -1213,6 +1247,7 @@ function conversationLine(one) {
     .join('  ');
   return `             ${one.id}  ${one.calls} call${one.calls === 1 ? '' : 's'}`
     + `${one.subagent_calls > 0 ? `  of which subagents: ${one.subagent_calls} call${one.subagent_calls === 1 ? '' : 's'}` : ''}`
+    + `${one.review_calls > 0 ? `  of which Codex's auto-review: ${one.review_calls} call${one.review_calls === 1 ? '' : 's'}` : ''}`
     + `${ran === '' ? '' : `  ${ran}`}`
     + `${used === '' ? '' : `  ${used}`}`
     + `${one.compactions > 0 ? `  compacted ${one.compactions}` : ''}`;
@@ -1275,6 +1310,7 @@ function jobLines(jobs, bots, head) {
     const [job] = jobs;
     return [
       `${head}  on, daily at ${job.at ?? job.cron}  job ${job.id}`,
+      ...(job.run === undefined ? [] : [`${more}Each run is a temporary ${job.run.harness} session: model ${job.run.model ?? `${job.run.harness}'s own`}, effort ${job.run.effort ?? `${job.run.harness}'s own`}.`]),
       `${more}Each run renews it; with no run, Claude Code ends it at ${job.expires}.`,
       `Turn it off:  ${groomCommand(bots)} --off`,
     ];

package/src/conversations.js

@@ -115,7 +115,8 @@ export function claudeSubagentTranscripts(file) {
 /**
  * The same conversations, each with the file the harness keeps it in, for a
  * caller that has to read what is inside one rather than only know it is there,
- * and whether the harness marks it as a subagent's.
+ * whether the harness marks it as a subagent's, and, for a Codex subagent, the
+ * conversation it was started for and whether it is Codex's auto-review.
  */
 export function transcriptsIn(harness, home, since) {
   const from = since === undefined ? 0 : Date.parse(since);
@@ -123,7 +124,13 @@ export function transcriptsIn(harness, home, since) {
   return found
     .filter((one) => Number.isNaN(from) || one.at >= from)
     .sort((left, right) => left.at - right.at)
-    .map((one) => ({ id: one.id, at: new Date(one.at).toISOString(), file: one.file, subagent: one.subagent === true }));
+    .map((one) => ({
+      id: one.id,
+      at: new Date(one.at).toISOString(),
+      file: one.file,
+      subagent: one.subagent === true,
+      ...(one.parent === undefined ? {} : { parent: one.parent, review: one.review }),
+    }));
 }
 
 /**
@@ -209,11 +216,29 @@ function codexConversations(home, from) {
     .flatMap((file) => {
       const meta = sessionMeta(file);
       return meta?.cwd === home && typeof meta.id === 'string'
-        ? [{ id: meta.id, at: Date.parse(meta.timestamp ?? '') || startedAt(file) || 0, file, subagent: isSubagent(meta) }]
+        ? [{ id: meta.id, at: Date.parse(meta.timestamp ?? '') || startedAt(file) || 0, file, subagent: isSubagent(meta), ...codexParent(meta) }]
         : [];
     });
 }
 
+/**
+ * Every Codex subagent on record, wherever it ran, with the conversation it was
+ * started for: `{ id, file, parent, review }` (#449). Found by the link in its
+ * own record, not by folder: a session's worker can run in a folder of its own.
+ * Read once per process, since every bot asks the same question of the same
+ * files.
+ */
+let subagents;
+export function codexSubagents() {
+  subagents ??= rollouts(codexDir()).flatMap((file) => {
+    const meta = sessionMeta(file);
+    if (meta === undefined || typeof meta.id !== 'string') return [];
+    const link = codexParent(meta);
+    return link.parent === undefined ? [] : [{ id: meta.id, file, ...link }];
+  });
+  return subagents;
+}
+
 /** Every rollout file under Codex's sessions folder, however deep it files them. */
 function rollouts(dir, depth = 0) {
   if (depth > 4) return [];
@@ -243,6 +268,21 @@ function sessionMeta(file) {
 const isSubagent = (meta) =>
   meta.source !== null && typeof meta.source === 'object' && 'subagent' in meta.source;
 
+/**
+ * The conversation a Codex subagent was started for, as its own record names
+ * it, and whether it is Codex's auto-review: `{ parent, review }`, or nothing
+ * for a session's own (#449). A session's spawned subagent names it under
+ * `source.subagent.thread_spawn.parent_thread_id`; Codex's auto-review, which
+ * is `{ subagent: { other: 'guardian' } }`, names the conversation it reviewed
+ * as a top-level `parent_thread_id` (tech notes, section 3).
+ */
+function codexParent(meta) {
+  if (!isSubagent(meta)) return {};
+  const parent = meta.source.subagent?.thread_spawn?.parent_thread_id ?? meta.parent_thread_id;
+  if (typeof parent !== 'string' || parent === '') return {};
+  return { parent, review: meta.source.subagent?.other === 'guardian' };
+}
+
 /** When a file was last written, for leaving out what is plainly too old. */
 function lastTouched(file) {
   try {