spectre-create_tasks

spectre-create_tasks is a skill for Claude Code from joenandez/spectre. It costs 50 tokens per session (1,731 once invoked), scanned A, original, MIT.

A workflow that turns approved requirements and a plan into a dependency-ordered task list and a short execution index.

In plain words
What is it for?
Use it before structured development to create or finalize tasks.json and execute.md for a scoped feature.
Why use it?
It gives implementation work a clear order and testable completion conditions without adding requirements that were not requested.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it before structured development to create or finalize tasks.json and execute.md for a scoped feature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joenandez/spectre/spectre-create_tasks
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.

Any agent
npx skills add joenandez/spectre --skill spectre-create_tasks
Clone the repo
git clone --depth 1 https://github.com/joenandez/spectre

Made for: Claude Code.

Wrote 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.

agentmods badge for spectre-create_tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_tasks/github.svg)](https://agentmods.dev/skills/joenandez/spectre/spectre-create_tasks)
Your own site
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-create_tasks"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_tasks/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.

agentmods 80×15 button for spectre-create_tasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-create_tasks"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-create_tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 69
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 5.1 $0.00050 $0.01731
Opus 5 $0.00025 $0.00865
Sonnet 5 $0.00010 $0.00346
Haiku 4.5 $0.00005 $0.00173

Measured 2d ago against content hash 6f1142a3b892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spectre-create_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.

plugins/spectre-codex/skills/spectre-create_tasks/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create_tasks

Purpose

Produce a scope-faithful task graph and compact execution index. The primary writes; research agents supply evidence only.

Inputs

  • $ARGUMENTS: explicit feature root/name or descendant requirements artifact; --depth xs|light|standard|comprehensive (default standard); mutually exclusive --tasks-only or --finalize-index; optional --orchestrated. Execute may supply finalized plan path/hash and closed-review evidence plus depth for a reviewed selected plan.
  • Read selected scope/summary, PRD, plan, UX, context, and research in full. Plan Out-of-Bounds and Verification are load-bearing. Thin requirements route to spectre-plan; never invent scope.

Working Set

  • Reuse a managed FEATURE_ROOT only when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and follow Skill(spectre-feature-root) through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged.
  • Repair stale feature/root metadata in artifacts this workflow touches.
  • Ensure {FEATURE_ROOT}/specs. Default pair: EXECUTE_FILE={FEATURE_ROOT}/specs/execute.md, DETAIL_FILE={FEATURE_ROOT}/specs/tasks.json; use same-basename feature-scoped pairs on collision. Fixtures: references/tasks.example.json, execute.example.md.
  • When targets/patterns are unclear, use read-only @spectre_finder, @spectre_analyst, or @spectre_patterns; skip for LIGHT/clear work. Agents return <=2,000 tokens; fold accepted evidence into task_context.md.

Outputs + DONE

tasks.json is indented, reparsed JSON with exactly meta and phases top-level keys:

  • meta: feature, feature_root, generated_at, schema_version, objective, scope, out_of_bounds, requirements_trace, architecture_context, coverage_summary.
  • Phase: id, title, summary, parents[].
  • Parent: id, title, description, predecessor, unblocks, optional risk, subtasks[].
  • Subtask: id, title, type, produces, consumed_by, replaces, context[], optional predecessor, acceptance_criteria[].
  • Context: path, anchor, note. Criterion: type (test|observable|state), text.
  • Task definitions are immutable during Execute: no lifecycle status, run/check/evidence data, index, indexes, wave_plan, or waves. Execution progress lives only in the local workflow store.

Read the full file on GitHub · 72 lines

Files

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.

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 Changed 6f1142a3b892
  2. 4d ago Changed 3ccac7e04c21
  3. 10d ago First seen · 72 lines · 50 tokens per session scan A 310beea22014

Subscribe to this mod's changes

spectre-create_tasks is a skill published in the GitHub repository joenandez/spectre (158 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,731 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories