cli-developer
Skill18 starsChanged 6 months agoMITView on GitHub
Review, modify, and improve the LenserFight CLI at apps/cli/. Covers citty commands, API client integration, output formatting, TUI, and configuration.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- santiago-migoni/claude-skillstheir own version, first seen Nov 8, 2026
- AxlZero21/Skillstheir own version, first seen Nov 8, 2026
- dirien/yet-another-agent-harnesstheir own version, first seen Nov 8, 2026
- lsyamsiar/claude-skillstheir own version, first seen Nov 1, 2026
- codeApe-7/ai-agent-workflowGrouptheir own version, first seen Nov 1, 2026
- hu465/claude-skills-their own version, first seen Oct 25, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- Jeffallan/claude-skills★ 12ksame name
- jshsakura/awesome-opencode-skills★ 30same name
- dirien/yet-another-agent-harness★ 19same name
- codeApe-7/ai-agent-workflowGroup★ 18same name
- belokonm/claude-supercode-skills★ 11same name
- PIXARTSeu/Synapse★ 9same name
- nicolasestrem/antigravity-gemini-skills★ 8same name
- HK-hub/AgentSkills★ 6same name
- zacklecon/claude-skills★ 3same name
- aptitude-stack/resolver★ 1same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-cost-manager-reducerSkill
- api-contract-reviewerSkill
- apps-language-rulesSkill
- contract-dto-consistency-reviewerSkill
- database-schema-reviewerSkill
- deep-code-reviewerSkill
- docs-managerSkill
- docs-publication-managerSkill
- feature-slice-designerSkill
- github-issue-solverSkill
- grasp-ooad-reviewSkill
- language-integratorSkill
- link-workspace-packagesSkill
- mcp-managerSkill
- migration-risk-reviewerSkill
- mobile-app-designerSkill
- mobile-app-integratorSkill
- mobile-app-product-ownerSkill
- mobile-app-reviewerSkill
- mobile-language-checkerSkill
- mobile-rulesetSkill
- mobil-ui-ux-rulesetSkill
- monitor-ciSkill
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
- product-owner-deciderSkill
- react-native-performance-reviewerSkill
- react-vite-performance-reviewerSkill
- release-readiness-reviewerSkill
- repo-architecture-auditorSkill
- repo-performance-guardSkill
- repository-pattern-reviewerSkill
- security-reviewerSkill
- smart-commitSkill
- supabase-api-rpc-reviewerSkill
- supabase-index-trigger-reviewerSkill
- supabase-rls-security-reviewerSkill
- supabase-schema-reviewerSkill
- tailwind-ui-ux-reviewerSkill
- ui-contract-guardSkill
- test-managerSkill
- unit-test-plannerSkill
- vite-performance-engineerSkill
- link-workspace-packagesSkill
- monitor-ciSkill
- nx-generateSkill
- nx-importSkill
- nx-pluginsSkill
- nx-run-tasksSkill
- nx-workspaceSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 73
Default (lf with no subcommand) → opens the first-party TUI dashboard (tui/dashboard.ts)
- Very specific: line 77
Never use fetch/axios directly — use callRpc / handleError from utils/api.ts
- Distinctive: line 78
Never add NestJS, Prisma, or backend dependencies
- Distinctive: line 79
Keep dependency footprint minimal (citty, consola, dotenv)
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Work on the LenserFight CLI (lf).
Scope
- Source:
apps/cli/src/** - Commands:
apps/cli/src/commands/*.ts - Utilities:
apps/cli/src/utils/(api, output, auth, auth-recovery, ansi, error-reporter, profiles, supabase-client, automation-objects, battle-stream-broadcaster, local-battle-engine, local-battle-paths, local-battle-storage) - Libraries:
apps/cli/src/lib/(exec-context, safety, telemetry, redact, onboarding, combine-seeds, command-inventory) - TUI:
apps/cli/src/tui/(dashboard.ts+tui/ink/— first-party dashboard, defaultlfbehavior;runtime-telemetry— shared withlf top) - Adapters:
apps/cli/src/adapters/
CLI Structure
src/main.ts— entry point, usesdefineCommand+runMainfrom citty; binary name islenserfight/lf- Each command file exports a
defineCommand(...)default and is lazy-imported inmain.ts src/utils/api.ts—callRpc+handleError; all Supabase RPC calls go through heresrc/utils/output.ts—printTable,printJson,truncate; uses consola for loggingsrc/utils/auth.ts+src/utils/supabase-client.ts— auth and Supabase clientsrc/utils/ansi.ts— ANSI helperAand symbolssymsrc/lib/exec-context.ts—setExecContext/getExecContextfor--local/--debugflagssrc/lib/safety/—assertSafefor input validationsrc/lib/telemetry.ts— telemetry adapter
Command pattern
import { defineCommand } from 'citty';
import consola from 'consola';
import { callRpc, handleError } from '../utils/api';
import { printTable, printJson } from '../utils/output';
const subCommand = defineCommand({
meta: { name: 'list', description: 'List items.' },
args: {
json: { type: 'boolean', default: false, description: 'Output as JSON' },
},
async run({ args }) {
try {
const data = await callRpc('fn_example', {});
if (args.json) printJson(data);
else printTable(['ID', 'Name'], data.map((r) => [r.id, r.name]));
} catch (err) {
handleError(err);
}
},
});
export default defineCommand({
meta: { name: 'example', description: 'Example group.' },
subCommands: { list: subCommand },
});Registration in main.ts
const main = defineCommand({
subCommands: {
example: () => import('./commands/example').then((m) => m.default),
},
});Global flags
--local→ setsLF_LOCAL=1(parsed early viaparseGlobalFlagsEarlybefore citty)--debug→ setsLF_DEBUG=1- Default (
lfwith no subcommand) → opens the first-party TUI dashboard (tui/dashboard.ts)
Constraints
- Never use fetch/axios directly — use
callRpc/handleErrorfromutils/api.ts - Never add NestJS, Prisma, or backend dependencies
- Keep dependency footprint minimal (citty, consola, dotenv)
- Output via
printTable/printJson/consola.*— never rawconsole.log - Build:
pnpm nx build cli| Test:pnpm nx test cli
References
- citty patterns and integration details: REFERENCE.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

