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 commands/habib0x0/spec-driven-plugin/spec-tasksgit 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 | $0.00013 | $0.00622 |
| Opus 5 | $0.00006 | $0.00311 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
spec-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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-tasks Command
Regenerate implementation tasks from the current spec requirements and design.
Model Override
When this command delegates task generation to the spec-tasker agent via the Task tool, check the SPEC_MODEL_TASKER environment variable. If it is set and non-empty, pass its value as the model: parameter to the Task tool invocation, overriding the agent's frontmatter default (standard tier). When unset, omit model: and the agent runs on its default.
Workflow
1. Identify Current Spec
Look for existing specs in .claude/specs/:
If multiple specs exist, ask which one to update. If only one exists, use it automatically.
2. Read Current Spec
Read:
.claude/specs/<feature-name>/requirements.md.claude/specs/<feature-name>/design.md.claude/specs/<feature-name>/tasks.md(if exists)
3. Analyze Changes
If tasks.md exists, compare against requirements and design:
- Identify new requirements not covered by existing tasks
- Identify design components without implementation tasks
- Identify tasks for removed/changed requirements
- Note completed tasks that should be preserved
4. Generate Updated Tasks
Create/update tasks organized by phase:
Phase 1: Setup
- Project scaffolding
- Dependencies
- Configuration
Phase 2: Core Implementation
- Main feature functionality
- Data models
- Business logic
Phase 3: Integration
- API connections
- Service integration
- UI integration
Phase 4: Testing
- Unit tests
- Integration tests
- E2E tests
Phase 5: Polish
- Error handling
- Edge cases
- Documentation
5. Preserve Completed Work
When regenerating tasks:
- Keep tasks marked as
completed - Update
pendingtasks if requirements changed - Mark obsolete tasks as removed with note
- Add new tasks for new requirements
6. Sync to Claude Code Todos
After updating tasks.md:
- Check existing todos with TaskList
- Create new todos for new tasks
- Update existing todos if descriptions changed
- Do not remove completed todos
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 · 115 lines · 13 tokens per session scan A f4ddaa64a510
spec-tasks is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 622 once invoked, about $0.0001 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 commands, from other repositories
receipts
Find the receipt. A dated line, or it did not happen.
ship
Deliver the increment. Then go live with a rollback you have run.
sruja-bugfix-triage
Systematic workflow for triaging and fixing bugs with architecture grounding.
triage
AI-powered reachability triage for dependency vulnerabilities. Scans for CVEs then searches your source code to estimate whether each vulnerable API is actually called. Outputs a prioritized FOUNDINSOURCE / UNCERTAIN / NOTFOUNDINGREP report.
smart-help
Context-aware help that suggests relevant commands.
crossframe-essay
使用 CrossFrame Essay 把用户给出的主题、素材或问题写成中文批判性洞察文章。.