agentmods.dev

suhail: Instructions file for Claude Code

CLAUDE.md

suhail CLAUDE.md is an instructions file for Claude Code from wessamfathi/suhail. It costs 2,314 tokens per session, scanned A, original, MIT.

Repository guidance for Suhail, a plan-orchestration pipeline for Claude Code. It explains the project layout, its role-based agents, slash commands, helper scripts, and tests.

In plain words
What is it for?
Understanding the repository structure, working on agents or commands, changing runtime scripts, and running the regression tests for Suhail.
Why use it?
It gives contributors the project facts and boundaries needed to change Suhail safely. It also points to the main validation command and important architectural details.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is wessamfathi/suhail's own configuration. It tells Claude Code how to work on suhail itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything suhail configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 2 changed 2d ago A scan 2,314 tokens original MIT
View the source file wessamfathi/suhail
Reuse

Borrowing it

Nothing to install: this file belongs to wessamfathi/suhail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wessamfathi/suhail/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wessamfathi/suhail

Made for: Claude Code.

Wrote 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.

agentmods badge for suhail CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wessamfathi/suhail/claude-md.svg)](https://agentmods.dev/instructions/wessamfathi/suhail/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wessamfathi/suhail/claude-md"><img src="https://agentmods.dev/badge/instructions/wessamfathi/suhail/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,314 This file is loaded in full into every session.
When invoked 2,314 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 5.1 $0.02314 $0.02314
Opus 5 $0.01157 $0.01157
Sonnet 5 $0.00463 $0.00463
Haiku 4.5 $0.00231 $0.00231

Measured 2d ago against content hash c34adb4270ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

suhail 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 2d 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working inside this repository.

What this repo is

Suhail is a generic plan-orchestration pipeline for Claude Code. The repo ships role subagents (agents/*.md), a slash-command-based orchestrator (commands/*.md), helper runtime scripts (scripts/), plugin manifests (.claude-plugin/), fixtures, and docs. It is itself a Claude Code project — when you open it in Claude Code you are working on the tool, not running it.

Repo layout at a glance

agents/                # Five role subagents: scout, executer, verifier, indexer, discover-planner.
commands/              # Eight slash commands: go, init, discover, next, auto, skip, status, abort. The orchestrator state machine lives in commands/go.md.
scripts/               # Runtime helper scripts, bash + PowerShell pairs (suhail-tick, suhail-read, suhail-write, suhail-clean).
skills/                # Front-desk skill: skills/su/SKILL.md — the bare /su menu/router.
tests/                 # Regression harness: tick matrix, reader/writer edge cases, payload validation. Run ./tests/run-all.sh.
fixtures/              # Plan files used to exercise Suhail end-to-end.
docs/                  # plan-format.md, architecture.md, extending.md, decisions.md, model-recommendations.md.
.github/               # CI workflow, issue form, PR template.
README.md              # User-facing.
CHANGELOG.md           # SemVer release notes.
LICENSE                # MIT.

Key architectural facts (do not forget)

  • The orchestrator is a slash command, not a subagent. It lives in commands/go.md. Earlier (v0.1.0) it was at agents/suhail.md; at the time that could not work because Claude Code subagents could not spawn nested subagents. Nested subagents have existed since Claude Code v2.1.172 (depth-limited), but the binding constraint today is a different one: AskUserQuestion — and interactive gates generally — is unavailable to subagents, and the orchestrator is built around interactive gates. The slash command body is injected into the top-level session, which can use the Agent tool to dispatch role subagents and can ask the user questions. Do not move it back into agents/. See docs/architecture.md § "Why the orchestrator lives in the slash command".
  • Subagent IPC is files-only. The orchestrator passes paths in prompts; subagents read inputs from disk and write outputs to disk. The orchestrator never echoes subagent bodies into the top-level conversation. Preserve this contract — it's why context stays bounded.
  • Subagents must not coordinate directly. Scout → executer is one-way. The verifier runs independently after the executer.
  • Domain knowledge flows through one channel. The verifier's audit pass is intentionally generic. Project-specific risks reach it only through brief.md's Domain risks worth flagging to auditor section. Do not bake domain rules into the verifier's prompt.

Read the full file on GitHub · 110 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. 2d ago Changed · +7 lines · +154 tokens per session c34adb4270ca
  2. 6d ago First seen · 103 lines · 2,160 tokens per session scan A 54dc1c301867

Subscribe to this mod's changes

suhail CLAUDE.md is an instructions file published in the GitHub repository wessamfathi/suhail (2 stars, last pushed 4d ago), licensed MIT. It adds 2,314 tokens to every session, about $0.0116 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.

ai-agentsautomationclaude-codeclaude-code-pluginclaude-code-skilldeveloper-tools
Related

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.

vercel/next.js · 7,296 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

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

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

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 · 4,469 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