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.
git clone --depth 1 https://github.com/hamza-ali-shahjahan/hamzaishWrote 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/commands/hamza-ali-shahjahan/hamzaish/setup)<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/setup"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/setup"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.01041 |
| Opus 5.5 | $0.00014 | $0.00416 |
| Sonnet 5.5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
setup 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bring this project's Claude Code file structure up to a healthy baseline. Safe to run on a fresh repo (scaffolds from scratch) or an existing one (extends what's there without clobbering).
Step 0 — Detect state
Before doing anything, check:
- Does
CLAUDE.mdexist? If yes, read it and judge whether it's healthy (covers project context, commands, code style, gotchas, references — under ~150 lines). - Does
.claude/exist? List its contents. - Is there a codebase to scan, or is this a fresh repo with only a spec/brief?
Report what you found in one short paragraph, then proceed.
Step 1 — CLAUDE.md
If healthy CLAUDE.md exists, leave it alone. Don't rewrite working content.
If missing or weak:
- If there's a codebase, run
/initfirst and then critically prune the generic filler that scaffolding emits. - If the repo is empty but a
SPEC.md/ brief / README exists, writeCLAUDE.mddirectly from that source. - If neither, ask the user for a one-paragraph project description before writing.
Target under 100 lines, five sections, in this order:
- Project context — what is this, what stack. One paragraph.
- Commands — only commands the user will actually run (build, test, lint, deploy). Skip default ones nobody types.
- Code style — non-default conventions only. Don't restate language defaults.
- Gotchas — project-specific warnings, weird workarounds, things that broke before.
- Reference docs — links to
docs/*.mdwith "read when..." annotations.
Every line earns its place. If something is discoverable in one session, leave it out — auto-memory will catch it.
Step 2 — Directory skeleton
Create if missing:
.claude/rules/— path-scoped rules.claude/commands/— slash commands.claude/skills/— local skillsdocs/— reference docs
Step 3 — Path-scoped rules
For each major subsystem, create .claude/rules/<subsystem>.md with YAML frontmatter:
---
paths: ["src/<area>/**"]
---
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.
- 1mo ago First seen · 102 lines · 34 tokens per session scan A f1a9074410f4
setup is a command published in the GitHub repository hamza-ali-shahjahan/hamzaish (11 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 1,041 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
status
A progress-check command for a project pipeline. It reads docs/STATE.md and compares its checklist with the project’s documented output files.
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.
my-tasks
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.