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/nikiforovall/claude-code-rules/reflectgit clone --depth 1 https://github.com/NikiforovAll/claude-code-rulesWhat 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 | $0.00024 | $0.00689 |
| Opus 5 | $0.00012 | $0.00345 |
| Sonnet 5 | $0.00005 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
reflect 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 2d 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.
Session Reflection
Create a reflective analysis of this Claude Code session.
Purpose
This reflection focuses on META aspects of the session - not what was implemented/fixed, but HOW the work was done:
- Techniques and approaches used
- What worked well vs. what didn't
- Lessons learned for future sessions
- Actionable improvements
Instructions
-
Analyze the Current Session
Review the conversation history and identify:
- Problem-solving approaches used
- Tool usage patterns (which tools, how effectively)
- Communication patterns (clarifications, iterations)
- Planning and execution strategies
- Any blockers, pivots, or course corrections
-
Generate the Reflection
Create a markdown file at:
.claude/reflections/<date>-<name>.mdWhere:
<date>is today's date inYYYY-MM-DDformat<name>is a short kebab-case slug (2-4 words) derived from the gist of the conversation (e.g.,api-debugging,test-refactoring,feature-planning)
Ensure the
.claude/reflections/directory exists before writing. -
Use This Structure
# Session Reflection: [Brief Title]
**Date**: YYYY-MM-DD
**Session Goal**: [One-line summary of what the session aimed to accomplish]
---
## What Went Well
- [Effective technique or approach]
- [Tool usage that was particularly helpful]
- [Communication pattern that worked]
## What Went Wrong
- [Approach that didn't work or caused delays]
- [Tool misuse or inefficiency]
- [Unnecessary iteration or backtracking]
## Lessons Learned
1. **[Lesson Title]**: [Explanation of the insight and why it matters]
2. **[Lesson Title]**: [Explanation of the insight and why it matters]
## Action Items
- [ ] [Specific improvement to apply in future sessions]
- [ ] [Process or workflow change to consider]
## Tips & Tricks for Claude Code
Based on this session, useful patterns for future reference:
- **Tip**: [Specific Claude Code tip discovered or reinforced]
- **Tip**: [Another useful pattern or shortcut]
## Generalization Opportunities
Consider creating reusable artifacts if this session revealed repeatable patterns. For example:
- **Slash Command**: [If a specific workflow could be automated]
- **Agent**: [If a specialized task could be delegated]
- **Skill**: [If a multi-step process with assets would help]
[Only include this section if genuinely applicable. Before generalizing, ensure the pattern is genuinely reusable across multiple contexts. Premature abstraction can add complexity without benefit.]
---
*Generated by `/reflect` command*
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.
- 2d ago First seen · 99 lines · 24 tokens per session scan A 8c65d625afd7
reflect is a command published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 689 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
gen-claude
Generate or enhance CLAUDE.md with project-specific guidance following best practices.
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.