Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sockulags/pult/claude-mdgit clone --depth 1 https://github.com/sockulags/pultWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sockulags/pult/claude-md)<a href="https://agentmods.dev/instructions/sockulags/pult/claude-md"><img src="https://agentmods.dev/badge/instructions/sockulags/pult/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00549 | $0.00549 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
pult CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
pult — projektpolicy
Electron-desktopapp (kontrollpanel för lokala utvecklingsappar). Svensk UI-text, engelska identifierare och commits.
Verifiering
npm test— vitest översrc/main/core/(ren kärnlogik, ingen Electron)npm run typecheck— tsc över main/preload (tsconfig.node.json) och renderer (tsconfig.web.json)npm run dev— manuell rök: fönster öppnas, inga fel i konsolen
Konventioner
- SQLite via Nodes inbyggda
node:sqlite— inga native moduler, ingen rebuild. Migreringar är append-only isrc/main/core/migrate.ts(user_version-styrda). - All logik som går att testa utan Electron ligger i
src/main/core/som rena funktioner med tester bredvid (*.test.ts). - IPC: kanaler registreras i
src/main/ipc.ts, exponeras typat isrc/preload/index.ts(window.pult). IngennodeIntegrationi renderer. - MCP: verktyg definieras mot det frysta kontraktet i
src/main/mcp/contract.tsoch läggs isrc/main/mcp/tools/(aggregeras itools/index.ts). Muterande verktyg går genom operations-/godkännandeflödet; env-VÄRDEN maskeras alltid (MASKED_VALUE) i MCP-svar — endast nyckelnamn får lämna appen. - Design: egna tokens i
src/renderer/src/styles.css(mörkt kontrollrum, mässingsaccent--brass, monospace för PID/port/kommandon). Referens idocs/mockup.html. Härma inte kända appars utseende. - Pult muterar aldrig ett smutsigt git-repo (
ensureBranch), och dödar bara processer den själv startat.
Gotchas
- Vitest kör under Node, appen under Electron — därför fungerar inte native
moduler med olika ABI här; det är skälet till
node:sqlitei stället för better-sqlite3. node:sqliteär experimentell: förväntaExperimentalWarningi loggar.- Processträd på Windows fälls med
taskkill /T /F; på POSIX används processgrupp (detached+kill(-pid)).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 38 lines · 549 tokens per session scan A 29ad709f3e90
pult CLAUDE.md is an instructions file published in the GitHub repository sockulags/pult (0 stars, last pushed 23d ago), licensed MIT. It adds 549 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).