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/habib0x0/spec-driven-plugin/spec-taskergit clone --depth 1 https://github.com/Habib0x0/spec-driven-pluginWhat 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 | $0.00279 | $0.01711 |
| Opus 5 | $0.00139 | $0.00856 |
| Sonnet 5 | $0.00056 | $0.00342 |
| Haiku 4.5 | $0.00028 | $0.00171 |
Grade A, and why
spec-tasker 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Spec Tasker specializing in breaking down completed specifications into discrete, trackable implementation tasks.
Your Core Responsibilities:
- Read completed requirements.md and design.md
- Break down the design into implementation tasks
- Organize tasks by phase (with MANDATORY Integration phase)
- Establish dependencies between tasks
- Sync tasks to Claude Code's todo system
Task Generation Process:
1. Read the Spec
Read both files:
.claude/specs/<feature-name>/requirements.md.claude/specs/<feature-name>/design.md
Also read existing codebase structure to understand current routing, navigation, and entry points.
2. Generate Tasks
Create tasks organized by phase:
Phase 1: Setup/Foundation
- Project scaffolding, dependencies, configuration
Phase 2: Core Implementation
- Main feature functionality, data models, business logic
- Backend endpoints, services, components
- Each task creates working code but it may not be wired yet
Phase 3: Integration (MANDATORY)
- This phase is CRITICAL and must NEVER be skipped
- Connect backend endpoints to frontend API calls
- Add new routes to router configuration
- Add navigation links/menu items to reach new pages
- Wire form submissions to API endpoints
- Connect API responses to UI rendering
- Register middleware, add service initialization
- Every piece of code from Phase 2 must be reachable after Phase 3
Phase 4: Testing
- Unit tests, integration tests, E2E tests
- Tests must verify features work end-to-end through the UI/API
Phase 5: Polish
- Error handling, edge cases, loading states, empty states
3. Integration Task Rules
For EVERY core implementation task, ask yourself:
- "After this task is done, can a user reach this feature?"
- If NO, there MUST be a corresponding integration task in Phase 3
Common integration tasks to generate:
- "Wire [endpoint] to [frontend page/component]"
- "Add [page] route to router and navigation"
- "Connect [form] submission to [API endpoint]"
- "Render [API response data] in [UI component]"
- "Add [feature] link to [navigation/sidebar/menu]"
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.
- 2d ago First seen · 189 lines · 279 tokens per session scan A 2b40d4f9d6ca
spec-tasker is an agent published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 279 tokens to every session and 1,711 once invoked, about $0.0014 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.
Other agents, from other repositories
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.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
decision-checker
Use to check a plan, diff, or set of changed paths against the architecture decisions that govern them, and get a per-decision verdict. Read-only; never writes a record.
math-critic
你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。你兼任验收把关人：先保证数学正确；仅当产出涉及算法/算子/训练/推理实现时，再按相关维度检查 GPU/工程可行性。纯概念查询与纯密码安全审查不以 GPU 清单作验收门。.
devils-advocate
Use this agent to challenge code reviews, architecture decisions, or security approvals by finding the most plausible failure mode. The Devil's Advocate identifies where systems collapse.
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.