agentmods.dev

cloclo CLAUDE.md

Project instructions for cloclo, an open-source command-line coding agent that can use different AI providers. They describe its source modules, generated build file, memory features, tools, and testing workflow.

In plain words
What is it for?
Use them when modifying cloclo, rebuilding its bundled Node.js command-line program, working on its agent features, or running its tests and checks.
Why use it?
They prevent edits from being lost by directing changes to the source files instead of the generated single-file runtime. They also provide the project conventions needed to build and test it correctly.

Instructions file

114 5mo ago A scan 1,973 tokens original MIT
View the source file SeifBenayed/cloclo
Install

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.

agentmods
npx agentmods add instructions/seifbenayed/cloclo/claude-md
Clone the repo
git clone --depth 1 https://github.com/SeifBenayed/cloclo
Per session 1,973 This file is loaded in full into every session.
When invoked 1,973 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01973 $0.01973
Opus 5 $0.00986 $0.00986
Sonnet 5 $0.00395 $0.00395
Haiku 4.5 $0.00197 $0.00197

Measured 3d ago against content hash 04c067691e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloclo 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 3d 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.

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cloclo (claude-native) — Project Conventions

Architecture

CRITICAL: claude-native.mjs is a BUILD OUTPUT. NEVER edit it directly. All source code lives in src/ (21 modules). Edit there, then run node build.mjs to regenerate claude-native.mjs. Any direct edit to claude-native.mjs will be lost on next build.

Source modules in src/ (dependency order): utils.mjs → config.mjs → providers.mjs → auth.mjs → security-rules.mjs → security.mjs → browser.mjs → tools.mjs → lsp.mjs → auto-memory.mjs → memory-metrics.mjs → memory-dream.mjs → audit.mjs → teams.mjs → sandbox.mjs → context-refs.mjs → smart-routing.mjs → skill-metrics.mjs (optional) → agent-metrics.mjs (optional) → aicl.mjs (optional) → cron.mjs → engine.mjs → session.mjs → index.mjs

Ink UI in ink-ui.mjs (runtime deps: ink, ink-select-input, ink-text-input, react). NDJSON bridge in claude-tool-loop.js (~943 lines, supports stream and mcp modes). gstack/ is a vendored skill/tool framework sub-project.

npm package: cloclo (v1.0.1). Binary: cloclo. Shipped files: claude-native.mjs, ink-ui.mjs, README.md, ROADMAP.md.

Testing & Build Workflow

node build.mjs              # Rebuild claude-native.mjs from src/
npm test                     # test-suite.mjs && test-loop.js && test-mcp.js
node test-suite.mjs          # Unit tests only (1542+ assertions)
node test-suite.mjs --e2e    # + live API calls (needs keys)
node test-suite.mjs --verbose # Verbose on failures

Baseline: git stash && node test-suite.mjs → 1453 passed, 0 failed, 13 skipped. Working tree has ~89 additional passing tests and 53 tests for unimplemented features (skill-metrics wiring, nudge system, CLI -p validation). These are test-ahead-of-implementation, not regressions.

After any code change: always node build.mjs then npm test (or at least node test-suite.mjs).

Test Patterns

  • Unit tests: Extract functions via extractBlock(), eval in isolated namespace. Beware: extractBlock counts braces — destructured default params like { type, since } = {} will break extraction. Use opts param + opts?.type instead.
  • E2E tests: runCLI(args, envOverrides, timeout) — spawns child process, captures stdout/stderr/exitCode.
  • Add new test sections before the // SUMMARY block (~line 7099) in test-suite.mjs.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 3d ago First seen · 108 lines · 1,973 tokens per session scan A 04c067691e5a

Subscribe to this mod's changes

cloclo CLAUDE.md is an instructions file published in the GitHub repository SeifBenayed/cloclo (114 stars, last pushed 5mo ago), licensed MIT. It adds 1,973 tokens to every session, about $0.0099 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 2026-08-30.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens