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/thewaywithin/agent-11/planarchivegit clone --depth 1 https://github.com/TheWayWithin/agent-11Wrote 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/thewaywithin/agent-11/planarchive)<a href="https://agentmods.dev/commands/thewaywithin/agent-11/planarchive"><img src="https://agentmods.dev/badge/commands/thewaywithin/agent-11/planarchive.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 5.1 | $0.00018 | $0.06471 |
| Opus 5 | $0.00009 | $0.03236 |
| Sonnet 5 | $0.00004 | $0.01294 |
| Haiku 4.5 | $0.00002 | $0.00647 |
Grade A, and why
planarchive 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 today.
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 — 835 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PLAN ARCHIVE COMMAND 📦
Command: /planarchive [options]
Purpose: Intelligently archive completed/stale content from tracking files using semantic analysis, size-based triggers, and duplication detection to keep them lean and token-efficient while preserving full historical record.
WHAT IS PLANARCHIVE?
PlanArchive is an intelligent content manager that uses semantic analysis to understand what content is truly active vs completed. It moves completed phases, old entries, and resolved issues from active tracking files (project-plan.md, progress.md) to archive files. This reduces token overhead when agents read these files while preserving complete project history.
Key Innovation: Unlike simple date-based archival, PlanArchive understands completion status, recognizes duplicated content, and generates summaries automatically.
KEY FEATURES
- Semantic Analysis: Understands completion status, dates, and section hierarchy
- Size-Based Triggers: Automatically archives large completed sections
- Duplication Detection: Identifies content duplicated across tracking files
- Smart Summaries: Auto-generates concise summaries of archived content
- User Control: Multiple modes (aggressive, analyze, target-based)
- Token Optimization: Reports estimated token savings
- Safe Archival: Preserves all content in archive files (reversible)
USAGE
# Interactive mode - analyze and confirm
/planarchive
# Analyze mode - see what WOULD be archived with reasoning
/planarchive --analyze
# Aggressive mode - archive ALL completed work regardless of age
/planarchive --aggressive
# Target size mode - archive until reaching specific line count
/planarchive --target-lines=1200
# Check for duplicates across tracking files
/planarchive --check-duplicates
# Archive entries older than 7 days (default: 14)
/planarchive --days=7
# Dry run - preview without making changes
/planarchive --dry-run
# Force mode - no confirmation prompts
/planarchive --force
# Archive only progress.md
/planarchive --progress-only
# Archive only project-plan.md
/planarchive --plan-only
# Disable summary generation (keep full content)
/planarchive --no-summaries
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.
- today First seen · 835 lines · 18 tokens per session scan A 0a89774c1202
planarchive is a command published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 13d ago), licensed MIT. It adds 18 tokens to every session and 6,471 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 2026-09-04.
Other commands, from other repositories
ensemble:generate-project-router-rules
Generate project-specific router rules by analyzing the project's tech stack.
ensemble:generate-router-rules
Generate router rules by introspecting installed agents and skills.
brainstorm
Facilitate a structured brainstorming session for feature development using Scrum Master techniques.
generate-prp
Generate comprehensive PRP (Product Requirements & Plans) with thorough research and validation.
execute-task
Execute individual development tasks from task breakdown documents.
execute-prp
Implement features from PRP specifications with comprehensive validation and testing.