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/whitequeen306/code-cortex-loop/cortexloop-architecturegit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat 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 | $0.00027 | $0.02141 |
| Opus 5 | $0.00014 | $0.01071 |
| Sonnet 5 | $0.00005 | $0.00428 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
cortexloop-architecture 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeCortexLoop Architecture
Analyze architectural coupling, detect refactoring opportunities, and optionally execute guided refactoring.
This is NOT part of the standard 7-pass pipeline. It runs independently for monthly/quarterly architecture reviews.
When to Use
- Monthly/quarterly architecture health checks
- Before refactoring sprints
- When modules become hard to test
- Before major releases
- When team discusses "this code is tangled"
What It Does
-
Analysis Phase (automatic)
- Build dependency graph
- Detect circular dependencies
- Detect God Objects (modules with too many responsibilities)
- Detect Feature Envy (modules over-dependent on others)
- Calculate coupling metrics (fan-in, fan-out, CBO)
-
Report Phase (automatic)
- Generate
docs/cortexloop/architecture-analysis.md(human-readable) - Generate
.cortexloop/architecture-cache.json(machine-readable) - Show summary in chat with priority-ranked coupling points
- Generate
-
Decision Phase (interactive)
- Ask: "要对这些耦合点执行重构吗？"
- Options: Yes (proceed to Phase 4) / No (stop, report saved)
-
Refactoring Phase (optional, interactive)
- Present 2-3 refactoring solutions per coupling
- User selects which coupling to fix
- Show detailed plan (steps, impact, cost, risk)
- Execute refactoring with user confirmation
- Run tests after each module refactoring
- Roll back on test failure
Command Variants
/cortexloop-architecture Default: analyze + ask refactor
/cortexloop-architecture --report-only Force report-only, skip refactor prompt
/cortexloop-architecture --auto-refactor High risk: skip confirmation (not recommended)
Default behavior (no flags) is recommended: analyze → report → ask user.
Workflow
Follow all steps in agents/architecture-analyst.md.
Agent: architecture-analyst
Skill: architecture-analysis
Load skill first, then follow agent workflow.
Output Artifacts
| File | Purpose |
|---|---|
docs/cortexloop/architecture-analysis.md |
Human-readable report with coupling details and refactoring solutions |
.cortexloop/architecture-cache.json |
Machine-readable cache for session recovery |
.cortexloop/refactoring-playbook.json |
Refactoring patterns that worked (optional, after successful refactoring) |
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 · 297 lines · 27 tokens per session scan A 2993adc3e2af
cortexloop-architecture is a command published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 2,141 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 2026-08-30.
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.