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 skills add attilaszasz/sdd-pilot --skill task-generationgit clone --depth 1 https://github.com/attilaszasz/sdd-pilotWrote 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/skills/attilaszasz/sdd-pilot/task-generation)<a href="https://agentmods.dev/skills/attilaszasz/sdd-pilot/task-generation"><img src="https://agentmods.dev/badge/skills/attilaszasz/sdd-pilot/task-generation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.03020 |
| Opus 5 | $0.00017 | $0.01510 |
| Sonnet 5 | $0.00007 | $0.00604 |
| Haiku 4.5 | $0.00003 | $0.00302 |
Grade A, and why
task-generation 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Generation Guide
Task Format (REQUIRED)
Every task MUST strictly follow this format:
- [ ] T### [P?] [US#|OBJ#?] {(FR|TR|OR|RR)-###?} [COMPLETES (FR|TR|OR|RR)-###?] Description with file path [after:T###?] [← T###:Symbol?] [→ exports: Symbol?] [VERIFY: <command>]?*
[VERIFY: <command>] is optional and repeatable (zero or more; typically 0–3). It appends after → exports: (and after [COMPLETES ...]). The command text runs from [VERIFY: to the next ] and MUST NOT contain a literal ] — move such checks into a verify script and reference it when needed.
Format Components
- Checkbox: Always
- [ ](markdown checkbox) - Task ID: Sequential (T001, T002...) in execution order
[P]marker: Only if parallelizable (different files, no dependencies)[US#|OBJ#]label: Required for delivery phases only- Product specs use
[US#]for user story phases - Technical and operational specs use
[OBJ#]for objective phases - Setup/Foundational phases: NO work-item label
- Polish phase: NO story label
- Product specs use
{(FR|TR|OR|RR)-###}tag: Links task to the requirement(s) it implements- Use
{FR-001}or{TR-001}for a single requirement,{FR-001,FR-003}for multiple - Required for tasks that directly implement a requirement
- Setup/infrastructure tasks with no direct requirement mapping may omit this tag
- Use
- Description: Clear action with exact file path
after:T###clause (optional): Explicit task-level dependency when a task depends on artifacts from a different phase or a non-adjacent task within the same phase. Omit when sequential T### ordering within a phase already implies the dependency.← T###:Symbolimport hint (optional): Lists specific symbols consumed from another task's output file, by source task ID. Use whendata-model.md,contracts/, or the Requirement Coverage MapFunction(s)/Symbol(s)column provide enough detail to name the symbols. Omit for leaf tasks with no cross-file coupling.→ exports: Symbol(params)export hint (optional): Lists the 1–3 most important symbols this task's file will export, with key parameter or field hints. Source fromdata-model.mdentities,contracts/schemas, or the Requirement Coverage MapFunction(s)/Symbol(s)column. Omit when no downstream task depends on this file.[COMPLETES (FR|TR|OR|RR)-###]marker (optional): Placed on the last task implementing a requirement that spans 3+ tasks. Signals the implementing agent to verify the full requirement chain at this task's completion.[VERIFY: <command>]annotation (optional, repeatable): A machine-checkable acceptance assertion the Developer MUST run from the repo root before marking the task[X]. Non-zero exit (for commands) or no match (forgreppatterns) is FAILURE — the task stays[ ]and routes into the error-recovery loop. Emit when a deterministic check is derivable: prefer aplan.md## Testing Strategytest command scoped to the task's file/requirement; else agrepfor a→ exports:symbol declaration; else a build/typecheck command targeting the task's file. Omit when no deterministic check is derivable. Commands MUST NOT contain a literal].
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 142 lines · 35 tokens per session scan A 33d267f1d45b
task-generation is a skill published in the GitHub repository attilaszasz/sdd-pilot (95 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 3,020 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
spec-driven-task-implementer
Use this skill when an approved Spec-Driven change has reached Phase 4 and the user wants a task, phase, or full feature implemented from .specs/changes/ . It executes tasks in order, updates task status immediately, verifies each task before completion, and should not be used before implementation approval.
next
Phase 3 of the Tripod workflow, run repeatedly. Finds the first unchecked task in TASKS.md, implements it under the rules in CLAUDE.md, verifies its "Done when" condition, checks the box, and commits. Use when the user says "next task", "continue", "keep going", or invokes /tripod:next.
tasks
Phase 2 of the Tripod workflow. Reads SPEC.md and CLAUDE.md, then writes TASKS.md — an ordered list of small, scoped, verifiable tasks that implement the entire MVP. Use after the user has reviewed their spec, when they ask to "create tasks" or "break down the work", or when they invoke /tripod:tasks.
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
speckit-converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
spec-kitty-implement-review
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…