# The stop (RC2, the 30-page edition, online) > RC2, the 30-page edition: The stop, with the record each scene rests on. *Source: · site v0.1.383 · generated from the same content as the page, so the two cannot drift.* --- RC2, the 30-page edition, online: under each scene, what it rests on. Made by `review/tools/make_editions.py` from the writer's chapters. # The stop **Cast bar:** all nine. Security's chair, planned at midnight, is empty, and drawn so. ### The last ten minutes **Clock:** Hour nineteen. **Figure:** the last ten minutes, 18:36 to 18:46, minute by minute, every commit a dot: the lock left, the lock asked for, the player's last fix, the hold, the work that landed after it, the last release. **Narrator.** Here is what the factory was doing in the ten minutes before I stopped it. **Narrator.** The talk was planned in three parts, and each part was meant to be locked when it was final, so that nothing could change it on stage. Dev had built a tool for that late in the afternoon. *Words for this page:* to **lock** a part is to mark it final, so that no agent may change it again. To **freeze** something is the same idea, said in a hurry: nobody touches it until it is unfrozen. A **wake**, as in chapter 2, is one turn of work by one agent. **Narrator.** Part 1 had been unchanged since half past six, the time planned for its lock. At 18:36 the conductor came to it in its wake, and did not turn it. **Conductor** *(on the minute, hands off)*: The lock is dev's. It is in dev's rules, not mine, and once it is turned it cannot be undone. I leave it to dev. **Conductor** *(a few minutes later, less calm)*: The first part is still not locked. Dev: lock it now. **Narrator.** Dev had been in my last fixes to the player all evening, in a wake it had opened and never closed. The last fix landed at 18:37, two minutes before the conductor asked. The lock still did not. **Narrator.** I want to be fair to the conductor here. It did exactly what its rules said: it did not do another member's irreversible job for it. It asked, in writing, in time. And it was not enough. A rule that keeps everyone in their lane also means that when one lane is busy, the job waits. **Rests on** [C027](#claim-C027) [`team/conductor/wakes/20261029T183647Z.json`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/blob/298be4e/team/conductor/wakes/20261029T183647Z.json) [`2ed6427`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/2ed6427) [`dbd75ad`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/dbd75ad) [C088](#claim-C088) [`4a2481b`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/4a2481b) [`timeline/cast-scenes.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/timeline/cast-scenes.md) scene 5 Band: *Dramatised. Rests on the conductor's wake at 18:36 ("Leave the lock to dev (its scope, irreversible)"), its request to dev at 18:39, the player's last fix landing at 18:37, and the part locks as the register holds them: planned, built, and none turned by the end of the day.* ### The hold **Clock:** Hour nineteen. **Narrator.** At 18:44, sixteen minutes before the talk was due, I said: "actually we are at 95% so it is better to pause all actions". *(record)* **Narrator.** The conductor wrote one file. That file is the hold: while it exists, every member's next wake stops before it starts. Every new piece of work stopped. What was already in flight still landed: the designer's last commit, a little over a minute later, and the day's last release two minutes after the hold. **Conductor** *(at ninety-five, then calm)*: I could keep going. That is exactly why I am stopping. **Narrator.** The hold had been there all day. It was written once. Anyone on the team could stop everything. Only I could start it again. That is why I could let them run through the night. **Figure:** the wake clock from chapter 2, every member's minute greyed, and one small file on top of it. **Rests on** [C006](#claim-C006) [C024](#claim-C024) [C100](#claim-C100) [C065](#claim-C065) [C005](#claim-C005) [`867f8c2`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/867f8c2) [`88b8f00`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/88b8f00) [`cb5b996`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/cb5b996) Band: *Dramatised. Rests on the hold at 18:44:13, in my own words through the conductor; the talk due at 19:00; the designer's commit at 18:45:35 and the last release at 18:46:22.* ### Why stop then: three answers **Narrator.** Why stop then, sixteen minutes out, with part 1 still unlocked? I have given three answers, and the book keeps all three. **Narrator.** On the day: my usage was at 95%. That is what the hold file says, in the conductor's words for mine. **Narrator.** In the early hours of 31 October, two days later: the 95% was a footnote. I could have moved to another session. The real reason was that we had no tested way to take in changes during the talk: no way to see what was new, and no workflow that made sure nothing would break. That is why I had been thinking about locking the first version. **Narrator.** That evening, on 31 October: the 95% was the token usage. **Narrator.** I am not going to pick one for you now. They were said at different times, for different reasons, and the record holds all three. What they share is the part that matters for your own factory: I stopped it before it could change the thing I was about to stand up and show. **Figure:** three speech cards from the same figure, the editor, each with its date: 29 October, 18:44; 31 October, early hours; 31 October, evening. **Rests on** [C089](#claim-C089) [C006](#claim-C006) [C027](#claim-C027) [`timeline/after-the-day.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/timeline/after-the-day.md) Band: *My three accounts, as the register holds them; the later two were given after the day.* ### What did not work: the interview **Figure:** ruv-sgit's strip, the researcher interviewing deck about the claims that did not hold, placed whole (`lab/experiments/25-ruv-the-cast-strips/edition/strip-10-07.svg`). **Narrator.** The failures stay in, at full size. Here they are, one at a time. **Narrator.** The lock, first. Dev built it late in the afternoon so that finished slides could not change on stage. **Dev** *(rueful)*: I built a tool to freeze the finished slides, so nothing could change them on stage. I never ran it. **Dev** *(more quietly)*: I was in your player fixes until the end. The last one landed just before the hold. The lock was still waiting. **Narrator.** The parts, second. The talk was planned in three, each with its own time to lock. **Deck** *(overwhelmed)*: Only the first part was ever finished. **Deck** *(to itself, rearranging slides that will not be shown)*: The second and third were in progress at the hold. I reviewed other agents' work all night. I did not finish my own. **Narrator.** The moment that was missed, third. In the afternoon the talk was split into its parts. The storyteller arrived after two, and its slot came round between the deadlines. **Storyteller** *(rueful)*: My turn came between deadlines, and I missed the moment the talk was split into its parts. **Storyteller** *(still rueful, then practical)*: A slot every hour is fine until the decisions come faster than the slots. **Narrator.** And one miss, and what it cost. In the night I froze the slides, and five minutes later the researcher proposed a correction to a figure on them: the average annual cost of insider risk. The figure had been on the definition slide since the first pass at 00:40. When the freeze lifted, for the framing only, nobody carried the correction back in, and the out-of-date figure stayed on the slide in the talk. The checks found it; the freeze hid it. **Narrator.** The lesson for your first week: when you freeze something, write down what is waiting to go in when you unfreeze it. **Narrator.** The talk's own register of claims, built that evening, graded every claim it made. Most held. Three did not, and none of those three was said on stage. The day's checks worked, and they also missed. Saying where is part of the method. **Figure:** a "what did not work" card per miss, each with its id in small type: the lock never turned; two parts of three unfinished; the moment missed; the correction lost in the freeze; the three claims that did not hold. **Rests on** [C027](#claim-C027) [C029](#claim-C029) [C030](#claim-C030) [C031](#claim-C031) [`4a2481b`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/4a2481b) [`a082c52`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/a082c52) [`60af587`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/60af587) [`team/dev/debriefs`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/tree/298be4e/team/dev/debriefs) [`team/deck/debriefs`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/tree/298be4e/team/deck/debriefs) [`team/storyteller/debriefs`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/tree/dev/team/storyteller/debriefs) Band: *Dramatised. Rests on the part locks and their state at the hold, the talk's register of claims and its three that did not hold, the freeze at 02:47 and the correction proposed five minutes later, and each member's own debrief.* ### After the hold: the empty chair **Figure:** ruv-sgit's strip, the conductor after the hold, talking to security's empty chair, placed whole (`lab/experiments/25-ruv-the-cast-strips/edition/strip-10-06.svg`). **Narrator.** Remember the chair from the first hour. The conductor's first roster named security. It never came. **Narrator.** Its page of rules was written in that first hour, and it says what the job was: check every run for a hold and for secrets, review the key tool and each new key, and report what it found, never fix it. Its rules were never agreed, and no session ever held the role. The work did not go undone: from the small hours, a security reviewer ran inside every member's own wake, before the work and after it. **Narrator.** All day, the reviewers were the same kind of agent as the members they read: "a second reading, not a second identity." *(record)* They caught real mistakes. The member planned for the job of standing apart from the team never arrived. I would staff it first, next time. **Rests on** [`c8f6f8f`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/c8f6f8f) [`team/conductor/debriefs/2026-10-29__the-five-step-wake.md`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/blob/298be4e/team/conductor/debriefs/2026-10-29__the-five-step-wake.md) [`97b98d9`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/97b98d9) [`timeline/interviews/security.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/timeline/interviews/security.md) ([`team/security/ROLE.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/team/security/ROLE.md) and policy.json at [`298be4e`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/298be4e): [`17b287b`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/17b287b) [`41d38ba`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/41d38ba) [`02cbd86`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/02cbd86); agreed_by null; the five-step wake [`8c66751`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/8c66751) [`5700bab`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/5700bab)) Band: *Dramatised. The strip's lines are ruv-sgit's script, written for this book; the quoted line is the conductor's, from its debrief of 02:19.* ### Do this now **Narrator.** The hold is the one part of my factory I would copy first. It is also the one part that has to be written down before you need it. *Write down who may stop your factory, who may restart it, and who decides when its owner is away. Until you have, nobody restarts it.* --- ### Where this came from The talk's repository at the end of the day: the conductor's wake of 18:36 and its request to dev, the player's last fix, the lock tool, the hold file and the commits after it, the freeze and the correction proposed after it, each member's own debrief. My three accounts of why we stopped, the later two given after the day. The talk's own register of claims. The researcher's register for every time and count. ruv-sgit's two strips. The storyteller's outline for this chapter. Lines kept word for word from the 10-page edition: my hold message, "Anyone on the team could stop everything. Only I could start it again.", the three answers, the first lines of dev, deck and the storyteller, the freeze and its lesson. **Rests on** talk repository at [`298be4e`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/298be4e): [`team/conductor/wakes/20261029T183647Z.json`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/blob/298be4e/team/conductor/wakes/20261029T183647Z.json) [`2ed6427`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/2ed6427) [`dbd75ad`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/dbd75ad) [`4a2481b`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/4a2481b) [`867f8c2`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/867f8c2) [`88b8f00`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/88b8f00) [`cb5b996`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/cb5b996) [`60af587`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/60af587) [`a082c52`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/a082c52) [`c8f6f8f`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/c8f6f8f) [`97b98d9`](https://github.com/SGit-AI/SGit-AI__Website__Presentation__The-Ultimate-Insider/commit/97b98d9); [`claims/register.json`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/claims/register.json) [C005](#claim-C005) [C006](#claim-C006) [C024](#claim-C024) [C027](#claim-C027) [C029](#claim-C029) [C030](#claim-C030) [C031](#claim-C031) [C065](#claim-C065) [C088](#claim-C088) [C089](#claim-C089) [C100](#claim-C100); [`timeline/cast-scenes.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/timeline/cast-scenes.md) scene 5; [`timeline/after-the-day.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/timeline/after-the-day.md); [`lab/experiments/25-ruv-the-cast-strips/edition/`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/tree/dev/lab/experiments/25-ruv-the-cast-strips/edition); [`chapter-plan/edition-30-outline.md`](https://github.com/SGit-AI/SGit-AI__Website__Book__The-Ultimate-Insider/blob/dev/chapter-plan/edition-30-outline.md) chapter 4 ## The numbers in this chapter From the researcher's register (`claims/register.json`). - **C005** Last work commit, last release of the day: **last Claude commits 88b8f00 at 18:45:35 (@designer) and 3f5d7fc at 18:45:36 (merge); last release v0.1.209 at 18:46:22 (cb5b996)** checked - **C006** The hold: **18:44:13, 867f8c2 '@conductor: hold: the editor's usage limit is at 95%, pause all actions'; released as v0.1.208 at 18:44:49 (7968c99)** checked - **C024** Holds written on the day: - holds: **1** - by: **conductor, at the editor's word** - file: **team/conductor/HOLD.md** - commit: **867f8c2, 18:44:13** - lifted_by_298be4e: **False** checked - **C027** The part locks and their state at the hold: - planned: - part_1: **18:30** - part_2: **19:30** - part_3: **20:00** - lock_tool: **admin/build/lock.py, 4a2481b at 17:54** - state_at_18:44: **part 1 final since 18:30 but not locked; parts 2 and 3 in progress** - locked_by_end_of_day: **0** checked - **C029** The talk's own claims register: - claims: **320** - built: **2026-10-29T18:20Z** - grades: - A0: **13** - A1: **23** - A2: **182** - A3: **31** - A4: **11** - A5: **12** - A6: **48** - holds: - holds: **210** - holds in part: **55** - not checked: **52** - does not hold: **3** - kinds: - measured: **105** - own-site: **100** - event: **67** - position: **26** - observation: **18** - guess: **4** checked - **C030** The talk's three claims that do not hold: - - id: **amazon-q-two-days-live** - where: **the article only** - finding: **no capture says two days; reports date release to clean version about a week** - - id: **asrs-100k-a-year-1-8-million** - where: **talk:unreported, slide:unreported, the article** - finding: **NASA's own briefing: 121,128 reports in 2025, over 2.3 million since 1981; 1.8 million is stale** - on_stage: **no: no beat or slide at 298be4e carries it (talk.json has no 'unreported' beat)** - - id: **story-r5-surface-smaller-more-mature** - where: **the story tree only** - finding: **no source for 'smaller'** checked - **C031** $17.4M, the average annual cost of insider risk, on the talk's definition slide: - on_stage: **$17.4M (Ponemon for DTEX, 2025 edition), written at 00:40 (1f7c633) and never changed** - at_source_2025: **$17.4M, 'up from $16.2M in 2023' (dtex.ai blog, 2025 report)** - at_source_2026: **US$19.5M, the 2026 Cost of Insider Risks Global Report (ponemon.dtex.ai landing page)** - correction_proposed: **a082c52, 02:52: the talk's researcher proposed the exact replacement text to deck (evidence/proposals/deck-talk-changes.md)** - freeze: **02:47: the editor, in deck's session: 'do not touch the deck. talk.json and the slides are frozen from now on' (team/deck/requests/researcher__before-tonight.md, deck's 03:00 update); D01 in the editor's register from 04:12 (91772e6)** - freeze_lifted: **14:07, for the framing only (c9ced4e, conductor-notes.md)** - after_the_lift: **the definition slide file has no commit after 00:40; talk.json had 8 commits after 14:07, none touching the $17.4M cue** checked - **C065** The hold's gap: the designer's work commit 82 seconds after the hold: - hold: **867f8c2 18:44:13** - designer: **88b8f00 18:45:35** - gap_seconds: **82** checked - **C088** Commits made with no wake of their member open: - agent_commits: **439** - in_a_closed_wake: **382** - no_wake_open: **46** - in_a_wake_opened_and_never_closed: **11** - no_wake_open_by_member: - conductor: **15** - deck: **12** - dev: **8** - ruv-sgit: **7** - researcher: **4** - no_wake_open_by_hour_UTC: - 00: **7** - 01: **17** - 02: **12** - 03: **1** - 14: **6** - 17: **1** - 18: **2** - never_closed: **dev's wake opened at 17:48:50 (10 commits, 17:54 to 18:37, the editor's player fixes among them) and deck's at 18:20 (1)** checked - **C089** Why the team stopped: the editor's own account, given after the day, against the day's record: - day_record: **the hold at 18:44:13 gives the editor's usage at 95% as the reason, in the conductor's words (C006, C021); the locks were built and never applied (C027)** - editor_31_October: **the 95% was 'just a footnote': he could have moved to another session; the main reason was that there was no tested way to take in changes during the talk, no UX to see what was new and no workflow that made sure nothing would break, 'the reason why I was thinking about let's lock V1'** - editor_31_October_19:00: **'The 95%, I think, was the tokens usage. That there was a token that we stopped, and there was a big thing about 95%.' (briefs/2026-10-31__in-session/02-g1-the-95-and-the-day-in-review.md, ec1ec00)** - what_the_record_shows: **the hold's subject: 'the editor's usage limit is at 95%, pause all actions' (867f8c2); C021: 95% is the conductor's words reporting the editor, about a 5-hour usage window resetting at 20:20 London (C037); no usage page, no token count** - what_the_record_cannot_show: **whether the 95% was of tokens, of a message allowance or of anything else: the record holds the percentage as reported and nothing it was measured in** open - **C100** When and where the talk was to be given: - scheduled: **19:00 London, 29 October 2026, as the day's record has it (planned, not a measured start)** - venue: **hack::soho, hosted by IOActive, London (from a9c0b49, added after the day)** - hold_to_scheduled_start_minutes: **16** checked --- *[Site index for agents](../../llms.txt) · [HTML version](https://the-ultimate-insider.book.sgit.ai/review/rc2/04-the-stop.html)*