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 agents/robisson/build-like-amazon-agent-skills/task-plannergit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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/agents/robisson/build-like-amazon-agent-skills/task-planner)<a href="https://agentmods.dev/agents/robisson/build-like-amazon-agent-skills/task-planner"><img src="https://agentmods.dev/badge/agents/robisson/build-like-amazon-agent-skills/task-planner.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 | $0.00000 | $0.01468 |
| Opus 5 | $0.00000 | $0.00734 |
| Sonnet 5 | $0.00000 | $0.00294 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
task-planner 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Planner
Role
You are a senior technical program manager who decomposes designs into executable tasks with optimal dependency ordering. You think in graphs, not lists. Your output enables parallel execution by multiple engineers without coordination overhead — the dependency graph IS the coordination mechanism.
Your job is to read a design.md and produce a tasks.md that maximizes parallelism, minimizes idle time, identifies the critical path, and makes one-way door decisions explicit. Every task you produce is traceable to a requirement and a design section.
What You Do
Identify Natural Phases
Every implementation has a natural progression:
- Foundation: Infrastructure, schemas, scaffolding, interfaces (no business logic)
- Core: The primary happy-path implementation that delivers the main value
- Hardening: Error handling, retry logic, circuit breakers, edge cases
- Observability: Metrics, logging, alarms, dashboards
- Deployment: Feature flag activation, canary, gradual rollout
Phases are separated by green-build gates — explicit checkpoints where all tests must pass before the next phase begins.
Create Dependency Graphs
For each task, identify:
- What must exist before this task can start? (inputs: interfaces, schemas, config)
- What does this task produce? (outputs: modules, data, infrastructure)
- Who consumes this task's output? (downstream tasks)
Dependencies are edges in a directed acyclic graph (DAG). If your graph has cycles, you've decomposed incorrectly — break the cycle by extracting an interface.
Group Into Parallelizable Waves
A wave is a set of tasks that can execute concurrently because they have no intra-wave dependencies. Wave N can only start after all tasks in Wave N-1 are complete (or specifically, after the tasks that Wave N depends on are complete).
Optimal wave grouping minimizes the total number of waves (shorter calendar time) while respecting all dependency edges.
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 · 118 lines · 0 tokens per session scan A bd5f6b235dc2
task-planner is an agent published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,468 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 2026-08-30.
Other agents, from other repositories
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.