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/fatihkan/badiWrote 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/fatihkan/badi/tasks)<a href="https://agentmods.dev/commands/fatihkan/badi/tasks"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/tasks.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 5.1 | $0.00000 | $0.00770 |
| Opus 5 | $0.00000 | $0.00385 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
tasks 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 today.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency-aware task sequencing command. Turns a plan or spec into an ordered, parallel-executable tasks.md — then runs it, fanning out independent ([P]) tasks concurrently and respecting dependencies. The execution layer between /eng-review (the plan) and the actual work.
Required Tools
- Read (the plan/spec, affected files)
- Grep / Glob (map files each task touches, to decide what is parallel-safe)
- Write (the tasks.md artifact)
- Workflow / Agent (execute
[P]tasks concurrently; sequential ones in order)
When to Use
After a plan exists (/eng-review, a spec, or a clear goal) and the work splits into many concrete steps. Use /tasks to make the dependency structure explicit and to actually parallelize the independent parts instead of doing everything sequentially. Not for a single-step change — that's just doing it.
Task Format (the artifact)
Write tasks.md (or .claude/workspace/tasks-<feature>.md) with one line per task:
- [ ] T001 [P] Create the data model in src/models/user.js
- [ ] T002 [P] Add the config schema in src/config/schema.js
- [ ] T003 Wire the service in src/services/user.js (depends on T001)
Rules:
T001,T002, … — sequential ids in execution order.[P]— parallel-safe: touches different files and has no dependency on an incomplete task. Tasks WITHOUT[P]run sequentially (they share a file or depend on an earlier task).- Explicit file path in every task — it's how you decide what is parallel-safe
(two
[P]tasks must not write the same file). - Phases when useful: Setup → Foundational (blocking) → per-feature → Polish.
Procedure
Step 1: Derive the task list
- Read the plan/spec. Break it into the smallest independently-verifiable tasks.
- For each task, name the exact file(s) it creates/edits and its dependencies.
Step 2: Mark parallelism
- Tag a task
[P]only if it touches files no other in-flight task touches AND all its dependencies are already complete. When unsure, leave[P]off (sequential is the safe default).
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.
- today First seen · 64 lines · 0 tokens per session scan A 4de88cce9483
tasks is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 770 tokens. 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 2026-09-06.
Other commands, from other repositories
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
plan-ceo-review
Strategic product gate — challenge the brief, find the 10-star product hiding inside the request, before writing any code.
routines-discover
Analyzes the current project to surface high-value Routines use cases across the three trigger types (schedule, API, GitHub events). Usage: /routines-discover.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
review-pr
Perform a comprehensive code review of a pull request.
git-worktree-clean
Clean up stale git worktrees with merged branch detection and disk usage report.