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/nahisaho/codegraphmcpserver/sdd-tasksgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.00000 | $0.03589 |
| Opus 5 | $0.00000 | $0.01795 |
| Sonnet 5 | $0.00000 | $0.00718 |
| Haiku 4.5 | $0.00000 | $0.00359 |
Grade A, and why
sdd-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 — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Tasks Command
Break down design into actionable implementation tasks.
Instructions for Claude
You are executing the /sdd-tasks [feature-name] command to create a task breakdown document.
Command Format
/sdd-tasks authentication
/sdd-tasks payment-processing
/sdd-tasks user-dashboard
Your Task
Generate a comprehensive task breakdown that transforms the design into actionable implementation tasks with full requirements traceability.
Process
1. Read Context
CRITICAL: Read these files first:
# Design and Requirements
storage/specs/{{feature-name}}-design.md
storage/specs/{{feature-name}}-requirements.md
# Steering Context
steering/structure.md
steering/tech.md
steering/product.md
2. Verify Prerequisites
Check design file exists:
❌ **Error**: Design document not found
Expected: storage/specs/{{feature-name}}-design.md
Please run `/sdd-design {{feature-name}}` first.
Tasks cannot be created without design (Article V: Traceability).
Check requirements file exists:
❌ **Error**: Requirements document not found
Expected: storage/specs/{{feature-name}}-requirements.md
Task breakdown requires requirements for traceability.
3. Generate Task Breakdown
Use template from templates/tasks.md.
Task Structure
Each task follows this format:
### TASK-XXX: [Task Title]
**Priority**: P0/P1/P2/P3
**Story Points**: [1/2/3/5/8/13]
**Estimated Hours**: [N]
**Assignee**: [Unassigned initially]
**Status**: Not Started
**Description**:
[Clear description of what needs to be done]
**Requirements Coverage**:
- REQ-XXX-NNN: [Requirement title]
- REQ-XXX-NNN: [Requirement title]
**Acceptance Criteria**:
- [ ] [Testable criterion 1]
- [ ] [Testable criterion 2]
- [ ] [Testable criterion 3]
**Dependencies**:
- TASK-XXX: [Dependency description]
**Test-First Checklist** (Article III):
- [ ] Tests written BEFORE implementation
- [ ] Red: Failing test committed
- [ ] Green: Minimal implementation passes test
- [ ] Blue: Refactored with confidence
**Implementation Notes**:
[File paths, code snippets, technical details]
**Validation**:
```bash
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 · 618 lines · 0 tokens per session scan A 0c3522fb17df
sdd-tasks is a command published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,589 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.