Repository navigation
Open
Description
TL;DR
- Model routing changed twice and settled on Opus 5.5. Code, prose and judgment default to
claude-opus-5-5-xhigh-fast, and no role runs above xhigh. Fable 5.2 runs outside a panel only when you name it or after two failed Opus 5.5 xhigh runs. Panels seat Fable 5.2, Opus 5.5 and Gemini 4 Neon atgemini-4-neon-xhigh. - Older
pstack-models.mdcrules keep their old lines until you rerun/setup-pstack, which migrates them./poteto-modereminds you once per session when the rule predates the# defaults: 3marker. - Many skill texts got much shorter.
/why,/how,/reflectand/architectare now short files with their reference files deleted, and the/poteto-modeplaybooks trace code directly instead of running/how. - Every agent
/poteto-modestarts now reads a newpoteto-mode/worker.mdfirst, so started agents see the operator's rules without a slash command loading them. /statechartnow has a path for native Windows, gives line and column for unreadable TLA+ specs, and draws parent states without arrows through their titles. The Windows work was not run on Windows.
Models and routing
- Defaults moved in two steps. #1236 dropped Grok 4.7 as a default everywhere and routed to Fable 5.2, Opus 5.5 and Gemini 4 Carbon. #1249 then made Opus 5.5 first. Code, prose and judgment default to
claude-opus-5-5-xhigh-fast, and Opus 5.5 always runs its-fastslug. No role runs above xhigh. Thehardest tasksrole is retired, and Fable 5.2 outside a panel runs only when the user names it or after two failed Opus 5.5 xhigh runs. #1236, #1249 - The Gemini panel seat moved from Gemini 4 Carbon to Gemini 4 Neon (#1283), then from
gemini-4-neon-hightogemini-4-neon-xhigh(#1284). This applies to arena runners, the arena cross-judge pool and interrogate reviewers. A Gemini seat runs atgemini-4-neon-xhighunless its line names another level. Neon has nomaxorfastslug, so the seat runs at its top slug. #1283, #1284 /setup-pstackwas reworked several times. It now writes# defaults: 3and offerslarge,mediumandsmallbudgets on a ladder that tops out at xhigh. It retires thehardest tasks,architect runnersand bothreflectroles, along with thewhyandhowroles. #1236, #1249- The
unlimitedbudget is removed, not capped, because it could only mean max. An oldunlimitedrule becomeslarge. #1249 - Migration of saved rules:
- A saved
gemini-4-neon-highpanel entry, or any non-Neongemini-4-*entry, becomesgemini-4-neon-xhigh. Other Neon levels a user picked stay. - The Gemini change keeps the
# defaults: 3marker, so/poteto-modedoes not ask anyone to rerun/setup-pstackfor it. Users with a saved rule move to Neon only when they rerun it. - #1283, #1284
- A saved
poteto-agentpinsclaude-opus-5-5-xhigh-fast. #1249- The Claude Code adapter doc (
docs/harness/claude-code.md) was updated in each of these four PRs to follow the new slugs. #1236, #1249, #1283, #1284
Changes to existing skills
/whyis one file with a 48-word body that names no data source or tool. It answers from the record, meaning the commits and PR discussions behind the target and each later change, and looks at other sources if that trail is thin. It cites what the authors wrote, marks its own inferences, and says what the record does not answer. The investigators, synthesizer, output format and all 12 files underwhy/references/are deleted. Answers are shorter, with no fixed headings. #1236/recallno longer borrows thewhyinvestigators. It starts its own investigator for each source. #1236/howis one file that starts one read-only subagent with a three-sentence brief and presents the output. The model routing, complexity gate, explorers, output format and both prompt templates are deleted./teachstill runs/howand/why. #1236/reflectis one file with no subagents, and its reference files are deleted. #1249 Before that, its drift example changed from a model-name rename to a function rename (parseConfigtoloadConfig), so the example does not age. #1236/architectis a short brief that sends large or contested designs to/arena. Its reference files are deleted. The cost is that the interface-depth wording from the longer text is gone. #1249/arenahas shorter runner and judge steps. #1249/sharpennow ends by having the rewritten prompt ask the agent to prototype any choice an experiment can settle and to recommend an option from what it observed. Product and preference choices that no experiment can settle stay with you. Before, every choice was left open. #1236/unslopand/technical-writingare shorter. #1249/blast-radius,/teachand/no-commentsno longer point at parts ofwhyandhowthat are gone./no-commentsnow says to trace the symbol or run/why. #1236- Fable (
claude-fable-*) counts as its own family, apart from other Claude models, so a panel with a Fable seat and an Opus seat stays diverse. #1236
Playbooks and principles
/poteto-modehas ten short triggers and shorter Subagents, reply and Playbooks sections. The Comments section is gone. The "nontrivial change, run how" trigger is gone, so a run no longer spends a step on/howbefore it designs or debugs. #1236, #1249- The new
poteto-mode/worker.mdis read first by every agent/poteto-modestarts. #1249 - The Orchestrate playbook is removed. Program-scale work routes to
/figure-it-out. #1249 - The Investigation, Feature, Bug fix, Hillclimb, Perf issue and Refactoring playbooks say "trace" where they said to run
how. #1236 - The Opening a PR, Babysit and Multi-phase plan playbooks are much shorter. #1249
- 14
principle-*skills are shortened. #1249 poteto-mode/scripts/check-plan.mjsand its test are deleted, since nothing runs them now. #1249- In the Benny automation skills, triage and reproduce trace the path themselves.
howleaves the list of pstack skills the target repository must resolve, and they still usewhy. #1236
Agents
comment-sickotraces the symbol or runs/why, matching/no-comments. #1236poteto-agentpinsclaude-opus-5-5-xhigh-fast. #1249
Fixes
/statechartran/bin/shfor its group kill and janitor, so it could not run on native Windows. TLC there ends lines with\r\n, and the readers split on\nonly. Marker matching failed, a broken rule produced "TLC exited 12 ... but its output names no rule that broke", and passing specs could report a wrong reason or leave raw@!@!@markers intlc.out. #1292- A shared
splitLineshelper now splits on\r?\n. kill.tsandjanitor.tsreplace the shell. The kill isprocess.kill(-pid, "SIGKILL")on macOS and Linux andtaskkill /t /fon Windows.- java and mise start with
windowsHide, the worker getsTEMPandTMP, and Java gets UTF-8 stdout and stderr flags. SKILL.mdsays to runnode --disable-warning=ExperimentalWarning <skill dir>/scripts/statechart.tson native Windows, because the launcher is a POSIX shell script.- On macOS and Linux the group kill, cleanup and output stay the same.
- A shared
/statechartnow reports the spec's line and column when SANY cannot read a TLA+ spec. Before, it showed the tail of SANY's XML run, a Java stack trace.check()reruns SANY in plain mode and reports from the first*** Errors,*** Abort messagesor*** Parse Errorline, capped at 40 lines. It falls back to the old tail if the rerun cannot start or has no error section. #1236/statechartcharts now enter a parent state through its border. Before, an arrow from outside to a state inside could cross the parent's title, which Pele 1.9.0 places after layout. The parent's start marker now carries the arrow on to the inner state, and a lone arrow keeps its label. #1236- It covers parents with one way in. A parent that two or more states lead into still draws direct arrows, and Pele can still route one through the title.
- Each such parent now shows a start marker, but the chart states the same steps. Of the corpus charts, only Login changes.
Docs
- The README and guide chapters 01 to 07, 09 and 10 follow the new routing, skill and playbook text. #1236, #1249, #1283
- The docs check now fails if a Grok slug comes back into the README or guide. #1236
How she did it
- She compared the two Gemini 4 Neon levels blind. Both caught every planted flaw.
gemini-4-neon-xhighfound more real problems nobody planted and took about 50% longer per run. She moved the panel seat to xhigh because panels are where pstack pays for depth. #1284 - For the Windows fix, the 34 new tests all fail on main and pass with the change.
- With real TLC made to print
\r\n, 8 of 33 corpus cases pass on main and 33 of 33 pass on the branch. - Everything ran on macOS. She states that nothing ran on Windows, so the Windows claims are inferred. #1292
- With real TLC made to print
- For the SANY change, the three new tests fail without the
run.tschange. The full statechart suite with the pinnedtla2tools.jarwas 50 of 50 on the corpus test and 373 of 373 after the parent-border change. #1236 - She states that no subagent had run on the new Fable 5.2, Opus 5.5 and Gemini slugs from the #1236 branch. #1236
- The test run in #1249 had one failure, the statechart symlink launcher test, which she says fails the same way on main on macOS. #1249
- Searches backed the cleanups. #1249 searched
pstack/formaxand found no routing above xhigh. #1283 searchedpstack/andharness/pstack/forcarbonand found 0 matches. #1236 searched for references to deletedwhyandhowfiles and roles and found only the retired-role example in/setup-pstack.
Cursor diff 0f77cd5...0b46ec3 · 5 PRs · summarised by claude-sonnet-5-5
Metadata
Metadata
Assignees
Labels
No labels
Activity