principle-build-the-lever
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
Skill by nahuelb
Chalk Labs
Need help deploying principle-build-the-lever?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nahuelb-principle-build-the-lever
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
principle-build-the-lever- Description
- Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Build the Lever When 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 genuinely 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. A reviewer will. - 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. - 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, so every delegate inherits the same hardened version instead of re-explaining it per prompt and watching each one drift. Keep it outside the delegates' write scope so they can't quietly edit the contract. - Applying this principle produces a file. If you cited it and there is no codemod, script, generator, or delegate skill in the diff, you didn't apply it. - Commit the lever when the work outlives the session, so the next run reruns it instead of redoing it. **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 [Laziness Protocol](../principle-laziness-protocol/SKILL.md), build the smallest script that does or proves the job, never a framework. 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).
From nahuelb/pstack-codex, MIT.
More from nahuelb/pstack-codex
- 0.564score
architect
nahuelb
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
arena
nahuelb
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: A★ 1Claude Code +9 - 0.549score
conversation-audit
nahuelb
Deeply audit a supplied Codex conversation for subagent and pstack-role token usage, model routing, timing, decisions, verification, and workflow performance.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
make-bot-ui
nahuelb
Use when building a local page or dashboard whose fixed buttons start approved Codex CLI tasks, with optional tailnet-only access.
SkillBFreshness: B★ 1Claude Code +9 - 0.524score
create-verification-skill
nahuelb
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillBFreshness: B★ 1Claude Code +9 - 0.524score
interrogate
nahuelb
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillBFreshness: B★ 1Claude Code +9 - 0.522score
figure-it-out
nahuelb
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
SkillBFreshness: B★ 1Claude Code +9 - 0.521score
no-comments
nahuelb
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillBFreshness: B★ 1Claude Code +9 - 0.519score
blast-radius
nahuelb
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/nahuelb/pstack-codex
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.561score
principle-build-the-lever
painhardcore
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: B★ 12Claude Code +9 - 0.308score
principle-build-the-lever
wayanjimmy
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: B★ 1Claude Code +9 - 0.308score
principle-build-the-lever
MRL-00
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: B★ 1Claude Code +9 - 0.305score
principle-build-the-lever
sammccord
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: B★ 1Claude Code +9 - 0.295score
principle-build-the-lever
skyisle
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: BClaude Code +9 - 0.292score
principle-build-the-lever
jR4dh3y
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: BClaude Code +9 - 0.292score
principle-build-the-lever
Graffioh
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: BClaude Code +9 - 0.292score
principle-build-the-lever
thiskevinwang
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillBFreshness: BClaude Code +9 - 0.265score
principle-build-the-lever
hvp17
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
SkillCFreshness: CClaude Code +9
More from nahuelb
- 0.565score
coordinator
nahuelb
Act as the coordinator of a long-running project.
SkillAFreshness: AClaude Code +9 - 0.564score
architect
nahuelb
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 1Claude Code +9 - 0.559score
arena
nahuelb
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: A★ 1Claude Code +9 - 0.549score
coordinator-setup
nahuelb
Set up Project Coordinator after installation.
SkillAFreshness: AClaude Code +9 - 0.549score
conversation-audit
nahuelb
Deeply audit a supplied Codex conversation for subagent and pstack-role token usage, model routing, timing, decisions, verification, and workflow performance.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
make-bot-ui
nahuelb
Use when building a local page or dashboard whose fixed buttons start approved Codex CLI tasks, with optional tailnet-only access.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get principle-build-the-lever running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
principle-build-the-lever skill. Agent Mart. https://agentmart.dev/skills/nahuelb-principle-build-the-lever (last updated 2026-10-24)