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/hudrazine/claude-code-memory-bank/plangit clone --depth 1 https://github.com/hudrazine/claude-code-memory-bankWrote 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/hudrazine/claude-code-memory-bank/plan)<a href="https://agentmods.dev/commands/hudrazine/claude-code-memory-bank/plan"><img src="https://agentmods.dev/badge/commands/hudrazine/claude-code-memory-bank/plan.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 | $0.00835 |
| Opus 5 | $0.00003 | $0.00417 |
| Sonnet 5 | $0.00001 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
plan 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detailed Analysis & Strategy Planning
Task
Think deeply about implementation strategy and develop comprehensive options.
$ARGUMENTS
Process
1. Technical Deep Dive
Building on initial understanding:
- Validate critical assumptions through code examination
- Analyze existing patterns and architectural constraints
- Examine edge cases and boundary conditions
- Review related tests for expected behaviors
For complex analyses, use TodoWrite to track findings and decisions
2. Risk Assessment
Identify and evaluate potential risks:
- High-impact changes: Database schemas, API contracts, authentication flows
- Performance implications: Algorithm complexity, data volume, caching needs
- Security considerations: Input validation, access control, data exposure
- Compatibility concerns: Breaking changes, dependency updates, browser support
Document critical risks in TodoWrite for tracking during implementation
3. Implementation Strategies
Develop multiple viable approaches:
For each approach:
- Implementation method and key steps
- Alignment with project patterns and coding principles
- Required changes and their scope
- Estimated complexity and timeline
- Specific risks and mitigation strategies
4. Comparative Analysis
Create decision matrix:
- Correctness: How well each solves the problem
- Maintainability: Long-term code health impact
- Performance: Runtime and resource implications
- Risk Level: Potential for introducing issues
- Effort: Implementation and testing time
5. Edge Case Planning
For the recommended approach:
- Null/undefined/empty state handling
- Boundary conditions and limits
- Error scenarios and recovery paths
- Concurrent access considerations (if applicable)
- Data integrity safeguards
Output
Implementation Options
Present 2-3 viable options in this format:
Option 1: [Descriptive Name]
- Approach: Brief description of implementation method
- Key Changes:
- Specific files and components affected
- New patterns or dependencies introduced
- Pros:
- Technical advantages
- Alignment with existing patterns
- Cons:
- Potential drawbacks
- Technical debt or complexity
- Risk Level: Low/Medium/High with justification
- Estimated Time: Realistic implementation timeframe
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 · 131 lines · 6 tokens per session scan A b7f57c95a824
plan is a command published in the GitHub repository hudrazine/claude-code-memory-bank (41 stars, last pushed 1y ago), licensed Unlicense. It adds 6 tokens to every session and 835 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
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.