rustyspec-tasks

An agent that turns a project plan into a story-driven task breakdown. It reads project context, a feature specification, and a plan, then fills in concrete tasks grouped by development phase.

In plain words
What is it for?
It is for creating setup, foundational, user-story, and polish tasks, marking tasks that can run in parallel, and linking them to user stories.
Why use it?
It removes the need to manually turn broad feature plans into ordered, actionable work items.

Agent

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 agents/jyjeanne/rustyspec/rustyspec-tasks
Clone the repo
git clone --depth 1 https://github.com/jyjeanne/rustyspec
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 153 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00009 $0.00153
Opus 5 $0.00005 $0.00077
Sonnet 5 $0.00002 $0.00031
Haiku 4.5 $0.00001 $0.00015

Measured 2d ago against content hash 385f7f39ef22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rustyspec-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 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.

.github/agents/rustyspec-tasks.agent.md · 19 lines

What it actually says

Read the project context from .rustyspec/AGENT.md.

Feature ID: $ARGUMENTS Find the matching directory under specs/. Read spec.md and plan.md.

Fill in tasks.md with concrete, actionable tasks:

  1. Define specific tasks with clear deliverables
  2. Organize by phases (Setup → Foundational → User Stories → Polish)
  3. Mark parallel-safe tasks with [P]
  4. Link tasks to user stories with [US1], [US2], etc.
  5. Replace all placeholder text with real content
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 First seen · 19 lines · 9 tokens per session scan A 385f7f39ef22

Subscribe to this mod's changes

rustyspec-tasks is an agent published in the GitHub repository jyjeanne/rustyspec (5 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 153 once invoked, about $0.0000 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.

Related

Other agents, from other repositories