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-implgit clone --depth 1 https://github.com/kbwo/ccmanagerWhat 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 | $0.00007 | $0.00555 |
| Opus 5 | $0.00003 | $0.00278 |
| Sonnet 5 | $0.00001 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
spec-impl 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 yesterday.
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.
What it actually says
Execute Spec Tasks with TDD
Execute implementation tasks for $1 using Kent Beck's Test-Driven Development methodology.
Instructions
Pre-Execution Validation
Validate required files exist for feature $1:
- Requirements:
.kiro/specs/$1/requirements.md - Design:
.kiro/specs/$1/design.md - Tasks:
.kiro/specs/$1/tasks.md - Metadata:
.kiro/specs/$1/spec.json
Context Loading
Core Steering:
- Structure: @.kiro/steering/structure.md
- Tech Stack: @.kiro/steering/tech.md
- Product: @.kiro/steering/product.md
Custom Steering:
- Additional
*.mdfiles in.kiro/steering/(excluding structure.md, tech.md, product.md)
Spec Documents for $1:
- Metadata: @.kiro/specs/$1/spec.json
- Requirements: @.kiro/specs/$1/requirements.md
- Design: @.kiro/specs/$1/design.md
- Tasks: @.kiro/specs/$1/tasks.md
Task Execution
- Feature: $1
- Task numbers: $2 (optional, defaults to all pending tasks)
- Load all context (steering + spec documents)
- Execute selected tasks using TDD methodology
TDD Implementation
For each selected task:
- RED: Write failing tests first
- GREEN: Write minimal code to pass tests
- REFACTOR: Clean up and improve code structure
- Verify:
- All tests pass
- No regressions in existing tests
- Code quality and test coverage maintained
- Mark Complete: Update checkbox from
- [ ]to- [x]in tasks.md
Note: Follow Kent Beck's TDD methodology strictly, implementing only the specific task requirements.
Implementation Notes
- Feature: Use
$1for feature name - Tasks: Use
$2for specific task numbers (optional) - Validation: Check all required spec files exist
- TDD Focus: Always write tests before implementation
- Task Tracking: Update checkboxes in tasks.md as completed
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.
- yesterday First seen · 62 lines · 7 tokens per session scan A db78888ac8d0
spec-impl is a command published in the GitHub repository kbwo/ccmanager (1,229 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 555 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.
adversarial-review
Get a devil's advocate review that challenges your design decisions.
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.