Repository navigation
Closed
Task
17 / 1717 of 17 issues completed
Copy link
Labels
wayfind: mapWayfind map: the /planning:wayfind issue whose sub-issues are its decision items.Wayfind map: the /planning:wayfind issue whose sub-issues are its decision items.
Description
Destination
Every topic of the talk has a decided outcome (build it, already have it, or declined with a reason), and each buildable one is a work item for a plugin or skill that includes a dogfooding step in this repository. Closes to /work-items:decompose.
Notes
- Skill every session on this map consults:
/discovery:research, before any recommendation that rests on outside evidence. - Method for every decision item (owner, 2026-11-12): start from the talk's own section for the item's chapter (the video frames, the transcript and the on-screen diagrams at the timestamps and slide numbers below), then weigh current research, Matt Pocock's skills as absorbed and this repository's existing plugins and setup, and converge on the best fit. A resolution that cites no slide or transcript passage is incomplete.
- Where a research item's result lands: its resolution comment on the item is the finding's home; the full findings file goes on this map's one dossier branch, which is never merged and is deleted when the map closes: dossier/15651-integrate-all-code-is-slop-talk.
- The talk: "All Code Is Slop (Except Mine)", Lauren Tan, AI Engineer Code Summit, 2026-11-11, video from 1:00:18 to 1:18:25. Her thesis: with agents, volume is free and trust is the constraint; buy trust cheapest and widest first (code shape, machine checks, verification, written rules, human review), turn every correction into a check, review evidence rather than diffs, and automate only a loop that already produces good work.
- Its ten chapters:
- Opening (slides 1-5): slop is relative; volume; "coding machines"; trust, not a "software factory".
- Trust model (6-11): two loops and the inverted pyramid; deterministic layers versus the prose judgment layer.
- Code is memory (12-16): the codebase is the largest input; gardening; copies breed copies.
- Examples (17-19): banned APIs, import bans, directory structure and file names as context.
- Escape hatches (20-22): unsolicited markdown and comments; the 99% comment ban.
- Corrections (23): every correction becomes a check whose message names the fix.
- Verification (24-28): review verification artifacts, not diffs; runtime verification with a feature map and driver CLI; TLA+ and Lean; UI property testing.
- Why now (29-32): most tokens go to verification; a 2018 chart of techniques per test stage; statecharts.
- Results (33-38): her team's pull request volume, releases, revert rate and performance.
- Order of work (39-44): lint first, clean up, strengthen verification, then automate; outer-loop triggers; a release run that explores the build and compares it with the last release.
- First region, the ecosystem-specifics and ladder Brief (locked in an interview, built separately from this map). Its outcomes:
- Generic skills stop shipping model-read language, framework and tool choices; each skill reads the consumer's own records, then infers from the repository.
- Executed adapters, single-tool plugins and security floors stay; an adapter names what it cannot read instead of skipping it.
- Shipped defaults that pick a tool, command or library are retired; unattended lanes run only what the repository states or its build files imply.
- The enforcement ladder becomes the one representation of the talk's pyramid: capability-named rungs, a verification tier in third place, a proportion rule in words, and her order of work (lint first, clean up, strengthen verification, then automate).
- The automation-gaps audit reports how a repository's enforcement is spread across the tiers; a review rule holds new enforcement-placing skills to the ladder.
- Constraints confirmed by the owner (C1-C11):
- C1: No shipped language specifics, applied to content that already ships.
- C2:
/corrections:codifyonly picks the rung and proves the check;/implementation:implementbuilds the rule in the consumer's own tooling. - C3:
/app-control:drivenever judges; the release pass is a whole-map scope on the existing live verification, not a new skill (revised 2026-11-12). Property testing and flood-style fuzzing are one thing, housed in the/testing:writeproperty guidance and not split by target. - C4: No issue or comment in a repository the owner does not own without the owner's permission, and the request says plainly it is not our repository.
- C5: The owner's own posture and this repository's is no code comments; plugins ship the keep-the-why default with the no-comments posture supported.
- C6: Quality bar is production: single responsibility, low coupling, high cohesion, things that change together live together, encapsulation, semantically accurate names.
- C7: Decisions hold only while aligned with the talk, its facts and data, and current research from official, authoritative sources.
- C8: Shipped skills that recommend, place or build enforcement or an instruction represent the pyramid's layers in order of preference, strongest to weakest, and say which to have most and least of.
- C9: Shipped skills adapt to the downstream context (repository, file, organization, user): they discover, research, then choose how to implement that layer there.
- C10: A skill reaches another only by its slash reference, presence-gated with a stated fallback, never its internals.
- C11: The whole talk is integrated into new or existing plugins and skills, and dogfooded in this repository; nothing she covered is left out.
- Facts already established:
- The video digest's home is the knowledge corpus plus a
docs/upstream/record. - A push to the default branch is already blocked:
maincarries a pull-request rule here and in the dotfiles repository. - One skill refers to another by
/plugin:skill, guarded by an "if installed" check with a documented fallback (docs/plugin-philosophy.md:101-116). - Five plugins carry a copy of the enforcement ladder: review, session-flow (retro), harness-config (automation-gaps audit), architecture (improve), corrections (codify) (
scripts/shared-copies.txt:91-95). - A consumer's records already layer user-global, team and personal settings, later layers overriding per key (
plugins/toolchain/reference/resolution-ladder.md:35-39). - Already have: the pyramid's order is the enforcement ladder (
plugins/review/context/enforcement-ladder.md:21-89); "every correction becomes a check" is/corrections:codify; the feature map and driver CLI are/app-control:mapand/app-control:drive; her no-comments command is/code-tidying:remove-comments; copies breeding copies is covered by/toolchain:ratchetand the code-tidying plugin. - Her team's numbers cannot be verified from outside, and her performance slide shows four measures that got worse.
- The video digest's home is the knowledge corpus plus a
- Decided work items (built off this map, each needs
/planning:interviewbefore build):- Adopt the no-comments posture here and support it as a plugin setting
- The formal-verification plugin, absorbing her three formal-verification skills in three slices (revised 2026-11-12; replaces the bounded proof of concept): Add the formal-verification plugin's chart skill, setup and consumer contract, proven on the loop-lane claim protocol, then Add the formal-verification specify skill's propose, create and check forms, then Add the formal-verification specify skill's refresh action
- Run a whole-map live verification pass on each release and report what is new since the last release
- Count corrections that became checks and generate the rule-to-enforcer inventory
- Suspect the observation method first when a verification fails in verification:confirm (agent-ready, no interview needed)
- Post the evidence comment from the ready step once the head is confirmed (agent-ready, no interview needed)
- Aligning app-control with her verification skills (agent-ready): drive steps state their result, preconditions and per-step evidence, launch and readiness, upkeep pass, driving conventions and control-tool traits
- Show typed commands in order, arguments, what runs for you and upstream equivalents in the skill cheat sheet (agent-ready; requested while working this map)
- Add a layout lens to architecture:improve that checks whether files that change together live together (needs its interview)
- From the smaller-ideas decision, needing interviews: loosened-gate review criterion, run-proven findings setting. Agent-ready: catch-up items and video offer, implement reads consumer idioms, premise check in the test-fix loop, smallest-change clause, error-message rule, recall sweep, type-discipline row, findings-file hand-off, upstream record update, property guidance covers every target
- The three dotfiles decision items (the stale multi-line commit message rule, checkable rules to hooks or permission rules, and the unproven redirect reason) are decided on this map and built in the dotfiles repository.
- Upstream record: docs/upstream/cursor-pstack.md, her pstack plugin absorbed.
- Spec container for the first region (the ecosystem-specifics plan, decomposed 2026-11-12): Resolve ecosystem specifics from the consumer repository and align the enforcement ladder with the talk's pyramid.
- Related: knowledge:video-digest: digest a time range of a video (--from/--to).
- Labels:
wayfind: interviewmarks a decision the owner makes;wayfind: researchan external-evidence question an agent can resolve;wayfind: taskdecision-unblocking work;needs-humankeeps an item off every autonomous frontier.
Decisions-so-far
- What did the interview on the talk already settle?: the interview's answered questions and the ecosystem-specifics Brief's acceptance criteria (resolved 2026-11-12)
- Which test-stage chart techniques apply to what consumers of a plugin marketplace build?: no technique-coverage lens; 26 of the 42 apply in a consumer repository and 25 are covered at least partly (resolved 2026-11-12)
- Which trust measures can this repository compute today?: revert rate is computable now, the no-human-touch share only as a lower bound, corrections converted to checks not at all (resolved 2026-11-12)
- Should a check's output have to name the fix, and be tested for it?: yes; every finding names a root-cause remedy first, covered checks are tested for it, this repository's 68 check scripts are held by a ratchet to zero, and a suppression-only script gets a real remedy or is deleted (resolved 2026-11-12)
- Should a plugin flag a new markdown file the task did not ask for, at write time?: declined; a hook cannot tell whether the task asked for a file, and every one of the 1,073 markdown files added in the last 300 commits here landed in a product or record path; reopen when an unrequested file is found merged (resolved 2026-11-12)
- Should the release exploring run keep a per-release baseline and report only new findings?: yes, inside the release pass itself; its report marks each finding new, pre-existing or gone against the last release, keyed by feature-map entry; no separate skill (resolved 2026-11-12)
- Should each verification check record the files it covers, so upkeep can classify a change?: already covered for runtime checks by control-skill
sourcesglobs and refresh triage; for formal models it is a requirement on the TLA+ proof of concept; no new build item (resolved 2026-11-12) - Should we adopt her two one-line verification rules, and in which skills?: yes; the replay rule lives in the formal-verification plugin, and "suspect the observation method first" goes once in
/verification:confirmwith an eval case (resolved 2026-11-12) - Should verification artifacts be shown in the pull request where a reviewer sees them?: already built as the one evidence comment posted after a confirmed head; the local ready step will post it too; no second place for evidence (resolved 2026-11-12)
- Should the feature map name a "what proves it works" part?: yes; every drive step states its observable result and each feature ends with a proof step, and app-control is aligned with her verification skills in five work items; four rejections on record stay (resolved 2026-11-12)
- Should folder-per-feature and file-suffix conventions be offered as derivable conventions?: not as shipped conventions; a style-agnostic layout lens on
/architecture:improvechecks whether files that change together live together (resolved 2026-11-12) - Which of five smaller pstack review and verification ideas should we take?: each idea and each gap from re-reading her whole plugin has a validated disposition; two reshaped takes need interviews, eight small items are filed, the rest are skipped with reasons (resolved 2026-11-12)
- Should the retro consider a check before a prose rule?: yes; the retro's catalog asks "could a check decide this?" first, lists its targets strongest first, and admits a prose rule only when no check can decide it, with one eval case (resolved 2026-11-13)
- Which of this repository's own checkable prose rules should get a check?: five, ranked by evidence (rules index in CI, as-of stamp without a recheck trigger, the follow-ups marker, docs pointers without a section anchor, price figures), plus aligning the force-push prose with its hook; four rules with no violations and no fix history are skipped (resolved 2026-11-13)
- Should the dotfiles instructions drop the stale multi-line commit message rule?: yes, the whole sentence; the hook stopped blocking multi-line messages the day the rule was written and its message names the fix (resolved 2026-11-13)
- Which low-friction checkable dotfiles rules should become hooks or permission rules?: stale prose fixed first; then the bypass-mode setting, a plugin hook on foreground waits, two deny rules and a Haiku spawn hook; three high-friction rules stay prose and the temp-worktree rule is on hold (resolved 2026-11-13)
- Should the unproven "redirects under the work directory are blocked" reason be verified or deleted?: verified false, the guard was removed the day the line was written; the line is deleted and two stale guardrails comments are fixed (resolved 2026-11-13)
Not-yet-specified (fog)
None left. The owner settled the four remaining points on 2026-11-13:
- Dogfooding depends on what the item produces, and the pull request body names which: a check runs in this repository's CI; a setting is set in
docs/conventions/; a skill gets one recorded run against this repository through/app-control:drive. - A release pass in a marketplace with no application of its own treats the skills as the app: it drives every entry of this repository's control skill at each plugin release. Details are settled in the interview on the release pass.
- No trust measure beyond the three already resolved, for now; revisited in the interview on the corrections count and rule-to-enforcer inventory.
- "Review evidence, not diffs" for a plugin pull request is the evidence comment plus the eval compare on any change to skill text. No new item.
Out-of-scope
- Her team's own numbers as targets: unverifiable from outside, and her performance slide shows four measures that got worse.
- A suppression expiry key: declined by the finding-suppression contract, which reports entries older than
exceptions.max_daysinstead (docs/contracts/finding-suppression/README.md:243-250). - Banning one specific API (her
useEffectexample) in a shared plugin: that is a consumer's rule, reached through/corrections:codifyand/implementation:implementin the consumer's own linter. - TLA+ or Lean as a default step: only as an opt-in tool chosen by the question.
Metadata
Metadata
Assignees
Labels
wayfind: mapWayfind map: the /planning:wayfind issue whose sub-issues are its decision items.Wayfind map: the /planning:wayfind issue whose sub-issues are its decision items.
Type
Fields
Work status
ready
Priority
medium
Activity
github-actions commentedon Nov 12, 2026
Size: Large
Complexity: Medium
Uncertainty: Knowable
Flags: none
Blocked by: none
I read this as a work-map tracking issue. Its goal is that every topic in the talk is decided (build, already have, or declined with a reason). Each buildable topic then becomes a work item that includes a dogfooding step in this repository. The map already lists four decided work items (#15647 to #15650) and several open sub-issues. The remaining fog (what "dogfooded" means per item, and how a release-exploring run applies to a marketplace) is by design and is being charted in those sub-issues, so I'm not raising a separate question here. No duplicate or merged fix found. The work is too big for one change and needs splitting, which the map already does.
Automated triage. A maintainer reviews it.
melodic-automation-lanes commentedon Nov 12, 2026
Not admitted to the issue lane yet: sub-issue #15657 is open; sub-issue #15658 is open; sub-issue #15659 is open; sub-issue #15660 is open; sub-issue #15661 is open; sub-issue #15662 is open; sub-issue #15663 is open; sub-issue #15664 is open; sub-issue #15665 is open; sub-issue #15666 is open.
6 remaining items
kyle-sexton commentedon Nov 13, 2026
Map closed: every decision, in full
All 17 decision items are closed and the frontier is empty. Each decision's home is its item's resolution comment; this comment states them together for
/work-items:decompose.Decisions
/testing:plangains a fuzz-target row and a consumer-driven contract-test row.sourcesglobs and refresh triage; for formal models it is a requirement on the formal-verification plugin. No new build item./verification:confirmwith an eval case./architecture:improvechecks whether files that change together live together.Also decided on this map: the formal-verification plugin in three slices, the release pass as a whole-map scope on the existing live verification, property testing and flood-style fuzzing as one guidance, and the cheat sheet extension. Their items are listed in the map's Notes.
Build items already filed
Listed in the map's Notes under "Decided work items", plus the first-region spec container with its 30 sub-items. Do not file these again.
Build items still to file (from decisions 13, 14, 16 and 17)
Each is one vertical slice with its own pull request, names its dogfooding step in this repository in the pull request body, and gives every new check a message that names the fix. A change to skill text opens with
do-not-mergeuntil its eval compare lands.plugins/session-flow/skills/retro/reference/ecosystem-improvement-catalog.md: a "could a check decide this?" step before the scope tree, routing to/corrections:codifywhen installed, else the Hooks section and the retro's ladder copy; target sections reordered Hooks and Settings, CLAUDE.md / Rules, Memory; "no rung above guidance can decide it" as the entry condition of CLAUDE.md / Rules; one eval case where a mechanical finding comes back as a check proposal. Settle whether the catalog's check thresholds duplicate codify'srecurrence.min_occurrences. Agent-ready.plugins/instruction-placement/git-hooks/index-check.shinto the hygiene checks. Agent-ready.as of YYYY-MM-DDmust hold a recheck trigger; shrink-only baseline for the 16 current hits. Agent-ready.Pre-existing (advisory):marker on follow-ups (decision 14).AGENTS.mdfirst says whether a non-advisory follow-up is allowed; then the pull-request contract step checks bullets under## Follow-ups. Settle whether the check lives here or inmelodic-software/ci-workflows. Agent-ready..claude/rules/cost-claims.mdstates. Agent-ready.plugins/guardrails/hooks/block-dangerous-git.sh:245accepts--force-with-lease --force-if-includes;AGENTS.mdallows only the pinned lease. Make the two agree. Agent-ready.untiland--watchwaits with a plugin hook (decision 16). Read the hooks reference first for whether a PreToolUse hook sees the Bash call's background flag. Agent-ready.plugins/guardrails/hooks/secret-pattern-detection.sh:336,403nameblock-hook-bypass, which no longer exists. Comment-only. Agent-ready.The dotfiles changes from decisions 15, 16 and 17 are built in the dotfiles repository and recorded on dotfiles #1556; they are not items here.
kyle-sexton commentedon Nov 13, 2026
Done (2026-11-13): Destination coherent, handed to /work-items:decompose.
kyle-sexton commentedon Nov 13, 2026
Reopened. All 17 decision items are closed and the closing comment above stands, but the map's Not-yet-specified section still holds four uncertainties the owner has not been asked about: what "dogfooded in this repository" means per item, how a release pass applies to a marketplace with no application of its own, what else counts as a trust measure, and whether "review evidence, not diffs" has an equivalent for plugin pull requests. An earlier edit to the map body today marked them covered by existing items without the owner's answer; that edit is reverted. The map closes again once the owner has settled each one.
kyle-sexton commentedon Nov 13, 2026
Done (2026-11-13): The owner settled the four Not-yet-specified points, now recorded in the map body. With the 17 decisions in the closing comment above, the destination is coherent and handed to
/work-items:decompose. The nine build items from the last five decisions are filed: 15935, 15933, 15936, 15937, 15938, 15939, 15940, 15941, 15942.feat(planning): wayfind chart proposes the whole map, routes its argu…
kyle-sexton commentedon Nov 15, 2026
Recorded from #15650 (owner, 2026-11-15): the trust measures stay at three. Covered: pull-request volume by deployment frequency in
/work-items:measure-delivery, and app performance by/performance:protect. Skipped: release cadence, because it follows the release bot's schedule, and contributors per month, because it is a per-person count. The count of corrections that became checks is #15650, and the share of merges no human touched is its own item.