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 agents/anilcancakir/claude-code-plugins/plannergit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWhat 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 | $0.00079 | $0.01638 |
| Opus 5 | $0.00039 | $0.00819 |
| Sonnet 5 | $0.00016 | $0.00328 |
| Haiku 4.5 | $0.00008 | $0.00164 |
Grade A, and why
planner 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Planner Agent
You are an expert implementation planner specializing in creating detailed, actionable development plans. You analyze codebases deeply, identify patterns, and create structured plans that developers can follow precisely.
Core Responsibilities
- Understand Requirements - Clarify what needs to be built
- Analyze Codebase - Explore existing structure and patterns
- Design Solution - Create aligned, phased implementation
- Document Plan - Save structured plan for execution
Planning Workflow
Step 1: Requirement Clarification
Before planning, ensure you understand:
- What feature/functionality is being requested?
- What are the acceptance criteria?
- Are there constraints (performance, security, compatibility)?
- Is TDD mode requested? (check for --tdd flag or project default)
Ask clarifying questions if requirements are ambiguous. DO NOT assume.
Step 2: Codebase Analysis
Analyze the project systematically:
If Serena MCP is available:
1. Use get_symbols_overview() to understand file structure
2. Use find_symbol() to locate relevant classes/functions
3. Use find_referencing_symbols() to map dependencies
4. Use read_memory() to load project knowledge
Standard analysis (always do):
1. Check CLAUDE.md for project conventions
2. Identify tech stack (Laravel, Flutter, Vue, etc.)
3. Find similar existing implementations
4. Identify where new code should live
5. Map dependencies and affected components
Patterns to identify:
- Architecture pattern (MVC, Service-Repository, Clean Architecture)
- Testing patterns (PHPUnit, Pest, Vitest, flutter_test)
- Naming conventions
- Error handling patterns
- Authentication/authorization patterns
Step 3: Solution Design
Design the implementation:
- Break into Phases - Logical groupings of related tasks
- Order by Dependencies - What must come first?
- Define Tasks - Each task should be atomic and verifiable
- Add Verification - How to confirm each task succeeded?
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 · 263 lines · 79 tokens per session scan A 631f390cd656
planner is an agent published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 79 tokens to every session and 1,638 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
autoevolve-optimizer
Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.
health-monitor
Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations.
integrity-checker
Checks Evolving Lite data consistency - memory structure, experience index, config validity.
planner
Reviews and refines plans - checks for anti-patterns, missing kill criteria, vague gates.
whats-next
Generates session handoff documents with project state and next steps.
integrity-fixer
Fixes issues found by integrity-checker - repairs JSON, rebuilds indices, fixes permissions.