Habit, a trial · installs only where you enable it
build-the-lever
about 730 tokens
build-the-lever as it installs, each line coloured by where its words came from.
- 2 files
- 2 edits
- 5 sentences left out
- 1 source
- last changed 2026-10-19
- trial
The text
description: "Build the tool that does or proves non-trivial work instead of doing it by hand: a codemod, a script, a generator, a query or a rerunnable check, proved against one unit done by hand and safe to rerun. Use when the work is more than a couple of obvious edits: many similar edits, a migration, an analysis over many files or rows, or a check you would otherwise make by eye."
greenlineOpens the trial habit: a lever for work beyond obvious editsbuild-the-lever is a trial habit, installed only where the workspace's `trials` names it, for the moment the work in front of you is more than a couple of obvious edits: many similar edits, a migration, an analysis over many files or rows, or a check you would otherwise make by eye, at whatever step the work is in, most often build. It writes no record of its own: the section of the step that runs names the lever and the check that proved it, recorded as a check, and since the record relies on the lever, it is committed with the change or, where it should not stay in the code, copied into the change's folder. You build and run the lever yourself, one agent in the one checkout. Making a recurring instruction a durable guardrail is `correct`'s, a trial start, and proving that an output is real is the verify step's.
pstackprinciple-build-the-lever/SKILL.mdWhen the work isn't trivial, build the tool that does it instead of doing it by hand.
**Why:** Two payoffs. Throughput: a codemod, generator, or script does the work the same way every time and reruns for free. Confidence: the tool is one artifact a reviewer can read and rerun to check the work. Hand-done changes can only be re-verified by redoing them. A deterministic script turns "trust me" into "run this".
**Pattern:** Default to building the lever. Skip it only when the task is trivial, a couple of obvious edits you can see at a glance.
- Do the first unit by hand to learn the recipe, then build the tool. Prove it by rerunning it on that unit and diffing against your hand-done version. Make the lever safe to rerun.
- Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification.
- A deterministic lever beats fan-out. If the tool can process every unit in one pass, run it yourself. Don't fan out delegates to hand-apply what a script can do.
pstackprinciple-build-the-lever/SKILL.md- Applying this principle produces a file. If you cited it and there is no codemod, script, or generator in the diff, you didn't apply it.
- Commit the lever when the work outlives the session.
**Balance:** The bar is triviality, not repetition. A one-off still earns a lever when the lever is what makes the work checkable. Per the ponytail habit, build the smallest script that does or proves the job, never a framework.
SKILL.md as installed, byte for byte SHA-256 03026cdb75f2d03ce9cc207cd0949fa97a9b0639e3a4d1efde601cc88fbfc618
references/greenline.md
about 110 tokens
The edits
Red is upstream's text; green is what greenline shipped in its place.
What the edit kinds mean
- method
- changes what the method does, under a recorded ruling
- correction
- fixes an error
- scope
- fits the text to this skill
- pointer
- re-points a reference
- smaller edits
- rename, relocate or adjust tool details
-
Upstream: If you cited it and there is no codemod, script, generator, or delegate skill in the diff, you didn't apply it.
Shipped: If you cited it and there is no codemod, script, or generator in the diff, you didn't apply it.
The lever is a codemod, script or generator, not a delegate skill
Full reason
The delegate skill belongs to the fan-out bullet dropped under R20, so the file the principle produces is a codemod, a script or a generator.
Ruling R1
-
Upstream: Per the [Laziness Protocol](../principle-laziness-protocol/SKILL.md), build the smallest script that does or proves the job, never a framework.
Shipped: Per the ponytail habit, build the smallest script that does or proves the job, never a framework.
The laziness protocol lives in ponytail now, so the link moves there
Full reason
The laziness protocol is grafted into the ponytail habit (S18a); the link to pstack's page, which the installation does not carry, points at ponytail.
What greenline wrote
The full reason for every passage greenline wrote, in the order of the text.
SKILL.md:8 scope
One opening paragraph in the habit's own voice: the situations its block row keys it by, that it is a trial installed only where trials names it, that it writes no record of its own and where the lever and its proof are named, that one agent builds and runs it, and the habits and steps beside it that own the neighbouring concerns its upstream pointers named. Since J-93 S2 the front names greenline's homes and commands by their nouns, their paths and commands on the skill's references page.
SKILL.md:10 pointer
The front points at the skill's references page, where greenline's paths and commands for it stand since J-93 S2, so the front holds the method alone.
references/greenline.md:1 scope
The skill's references page opens: greenline's mechanics for the skill, the paths and commands its front names by their nouns, held apart from the upstream prose since J-93 S2.
references/greenline.md:5 relocate
build-the-lever's mechanics: the lever's check recorded through greenline check and its copy in the change's folder, held apart since J-93 S2.
What it left out
pstack
pstack, principle-build-the-lever/SKILL.md: 5 of 27 sentences left out
- When you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch fences in one artifact.
- Keep it outside the delegates' write scope so they can't quietly edit the contract. 2 sentences left out: The bullet for fanning work out to subagents is dropped: greenline runs one agent at a time, and its line that a deterministic lever beats fan-out stands (R20). R1
- 6 sentences taken
- Distinct from [Encode Lessons in Structure](../principle-encode-lessons-in-structure/SKILL.md), which makes a recurring instruction a durable guardrail.
- This is throughput and reviewability on the work in front of you.
- For scripting the verification itself, see [Prove It Works](../principle-prove-it-works/SKILL.md). 3 sentences left out: The pointers to pstack's encode-lessons and prove-it-works pages, which the installation does not carry, become the opening paragraph's neighbours: correct and the verify step. replaced by line 8 of SKILL.md
The ledger entry
greenline's ledger logs how each skill was made and changed, with a reason for each entry.
2026-10-19 2026-10-19-build-the-lever-front-and-references
build-the-lever's paths and commands move to a references page
The front names greenline's homes and commands by their nouns and points at a references page, which holds their paths and commands (J-93 S2).
- Authorised by
- 2026-10-18 The operator's words of 2026-10-18 on the redesign (N-56, items 2 and 7), "we need the upstream prose upfront and references hold how to work meaning the artefacts etc" and, on the ingest procedures, "we wanna have there prose .. what we don't wanna have is there artefact system and fit them to use ours"; and J-93 S2's finalise words of 2026-10-19, "Fast route, merged slices, parallel jobs (Recommended)": a skill's front is the upstream prose its recipe cuts, and its mechanics, where its work lands, its section's form, its depths at each mode and its commands, stand on its references page
Rulings, R1 to R4
- the operator's rulings of 2026-10-08 on the intake R3 ("everything is good", and "yes go ahead" on the portable forms of R21), the verdicts standing and every contradiction ruled as recommended; principle-build-the-lever is a copy, a new trial habit build-the-lever, its fan-out bullet dropped under R20 of 2026-10-07: greenline runs subagents one after another, never in parallel, and uses no worktrees ("we are not doing worktrees and parralel susbs at all ... only linear sub flow")
- under R22 of 2026-10-08, the re-cut brief accepted as recommended ("yes amend, with one change"): the names of the roster table and the trial names stand, and show-me stays implicit
- J-59, on the operator's words of 2026-10-09 ('okay then implement all of this'): a gist of at most twelve words on every account whose reason is stated; no text, measure or method changes
- The operator's words of 2026-10-18 on the redesign (N-56, items 2 and 7), "we need the upstream prose upfront and references hold how to work meaning the artefacts etc" and, on the ingest procedures, "we wanna have there prose .. what we don't wanna have is there artefact system and fit them to use ours"; and J-93 S2's finalise words of 2026-10-19, "Fast route, merged slices, parallel jobs (Recommended)": a skill's front is the upstream prose its recipe cuts, and its mechanics, where its work lands, its section's form, its depths at each mode and its commands, stand on its references page
2 earlier entries
2026-10-09 2026-10-09-build-the-lever-gists
Every account gets a short gist for the website
2026-10-08 2026-10-08-build-the-lever-recipe
Enters as a trial habit copied from pstack
Pages it touched: SKILL.md