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/kbwo/ccmanager/spec-requirementsgit clone --depth 1 https://github.com/kbwo/ccmanagerWrote 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/kbwo/ccmanager/spec-requirements)<a href="https://agentmods.dev/commands/kbwo/ccmanager/spec-requirements"><img src="https://agentmods.dev/badge/commands/kbwo/ccmanager/spec-requirements.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 | $0.00006 | $0.01188 |
| Opus 5 | $0.00003 | $0.00594 |
| Sonnet 5 | $0.00001 | $0.00238 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
spec-requirements 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 3d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Generation
Generate comprehensive requirements for feature: $1
Context Validation
Steering Context
- Architecture context: @.kiro/steering/structure.md
- Technical constraints: @.kiro/steering/tech.md
- Product context: @.kiro/steering/product.md
- Custom steering: Load all "Always" mode custom steering files from .kiro/steering/
Existing Spec Context
- Current spec directory: !
bash -c 'ls -la .kiro/specs/$1/' - Current requirements:
.kiro/specs/$1/requirements.md - Spec metadata:
.kiro/specs/$1/spec.json
Task: Generate Initial Requirements
1. Read Existing Requirements Template
Read the existing requirements.md file created by spec-init to extract the project description.
2. Generate Complete Requirements
Generate an initial set of requirements in EARS format based on the project description, then iterate with the user to refine them until they are complete and accurate.
Don't focus on implementation details in this phase. Instead, just focus on writing requirements which will later be turned into a design.
Requirements Generation Guidelines
- Focus on Core Functionality: Start with the essential features from the user's idea
- Use EARS Format: All acceptance criteria must use proper EARS syntax
- No Sequential Questions: Generate initial version first, then iterate based on user feedback
- Keep It Manageable: Create a solid foundation that can be expanded through user review
- Choose an appropriate subject: For software projects, use the concrete system/service name (e.g., "Checkout Service") instead of a generic subject. For non-software, choose a responsible subject (e.g., process/workflow, team/role, artifact/document, campaign, protocol).
3. EARS Format Requirements
EARS (Easy Approach to Requirements Syntax) is the recommended format for acceptance criteria:
Primary EARS Patterns:
- WHEN [event/condition] THEN [system/subject] SHALL [response]
- IF [precondition/state] THEN [system/subject] SHALL [response]
- WHILE [ongoing condition] THE [system/subject] SHALL [continuous behavior]
- WHERE [location/context/trigger] THE [system/subject] SHALL [contextual behavior]
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.
- 3d ago First seen · 130 lines · 6 tokens per session scan A db94e30c32fa
spec-requirements is a command published in the GitHub repository kbwo/ccmanager (1,229 stars, last pushed 4d ago), licensed MIT. It adds 6 tokens to every session and 1,188 once invoked, about $0.0000 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.
Other commands, from other repositories
package-assistant
Convert an OfficeCLI skill into a fully wired AionUi assistant preset, or update an existing one.
implement
Have Gemini (via agy) implement a task by editing files directly.
ask
Ask Gemini (via agy) a question, optionally with file context.
rescue
Delegate investigation, an explicit fix request, or follow-up rescue work to the Gemini rescue subagent.
review
Run a Gemini code review against local git state.
task
Delegate a task to Gemini CLI as a background or foreground job.