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/kaze-jp/kusa/spec-tasksgit clone --depth 1 https://github.com/kaze-jp/kusaWrote 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/commands/kaze-jp/kusa/spec-tasks)<a href="https://agentmods.dev/commands/kaze-jp/kusa/spec-tasks"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/spec-tasks.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00765 |
| Opus 5 | $0.00000 | $0.00382 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
spec-tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Implementation Tasks
Break a technical design into concrete implementation tasks with parallel execution analysis.
Usage
/kiro:spec-tasks <feature-name>
Instructions
-
Read the design document from
.kiro/specs/$FEATURE_NAME/design.md. If it does not exist, instruct the user to run/kiro:spec-designfirst. -
Read the requirements from
.kiro/specs/$FEATURE_NAME/requirements.mdfor traceability. -
Read project structure from
.ao/steering/structure.mdto understand file organization. -
Break the design into tasks. Each task must include:
- Task ID: T-001, T-002, etc.
- Title: Short descriptive name
- Description: What needs to be done
- Files to create/modify: Explicit file paths
- Dependencies: Other task IDs that must complete first
- Acceptance criteria: How to verify the task is done
- Test requirements: What tests to write
- Estimated effort: Small (< 1hr), Medium (1-2hr), Large (2-4hr)
-
Apply task generation rules:
- Each task should be 1-4 hours of work maximum
- Tasks must be independently verifiable
- No task should modify more than 5 files
- Shared utilities should be separate tasks that others depend on
- Test tasks can be bundled with implementation tasks
-
Perform parallel execution analysis:
- For each pair of tasks, check if they modify the same files
- Tasks that share NO file dependencies can be marked with (P)
- Tasks that share files MUST have explicit ordering via dependencies
- Document the conflict matrix showing which tasks share files
-
Generate
tasks.mdwith this structure:
# Implementation Tasks: <feature-name>
## Document Info
- Feature: <name>
- Total tasks: <count>
- Parallelizable: <count of (P) tasks>
- Created: <date>
## Task Dependency Graph
<ASCII visualization of task dependencies>
## Parallel Execution Groups
<Groups of tasks that can run simultaneously>
## Tasks
### T-001: <title> (P)
- **Description**: <what to do>
- **Files**: <file paths to create/modify>
- **Dependencies**: None
- **Acceptance Criteria**:
- [ ] <criterion 1>
- [ ] <criterion 2>
- **Tests**: <test requirements>
- **Effort**: Small | Medium | Large
### T-002: <title>
- **Dependencies**: T-001
...
## File Conflict Matrix
| Task | Files | Conflicts With |
|------|-------|---------------|
| T-001 | src/foo.ts | None |
| T-002 | src/foo.ts, src/bar.ts | T-001 (src/foo.ts) |
## Requirements Traceability
| Requirement | Tasks |
|------------|-------|
| FR-001 | T-001, T-003 |
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 · 99 lines · 0 tokens per session scan A 8dd01cdb2986
spec-tasks is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 765 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.