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/fomo-driven-development/strategic-claude-base/summarizegit clone --depth 1 https://github.com/Fomo-Driven-Development/strategic-claude-baseWrote 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/fomo-driven-development/strategic-claude-base/summarize)<a href="https://agentmods.dev/commands/fomo-driven-development/strategic-claude-base/summarize"><img src="https://agentmods.dev/badge/commands/fomo-driven-development/strategic-claude-base/summarize.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 | $0.00010 | $0.02135 |
| Opus 5 | $0.00005 | $0.01068 |
| Sonnet 5 | $0.00002 | $0.00427 |
| Haiku 4.5 | $0.00001 | $0.00214 |
Grade A, and why
summarize 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are tasked with creating implementation summaries that focus on problems, incomplete work, and outstanding issues from the current work session. You should be problem-focused, session-scoped, and work only with uncommitted changes and current context.
Plan reference (optional): $1
Initial Response
When this command is invoked:
-
Check for uncommitted work first:
git status --porcelain -
If uncommitted changes exist, proceed immediately to context analysis
-
If there are no uncommitted changes, respond with:
I don't see any uncommitted changes in your repository. A summary documents the problems and incomplete work from your current implementation session. Please: 1. Complete some implementation work, or 2. Specify what you'd like me to summarize if you've already committed your changes Usage: `/summarize` - Auto-detect current work Usage: `/summarize PLAN_0001_...` - Summarize work for specific plan
Process Steps
Step 1: Current Session Context Analysis
-
Check uncommitted changes:
# Check what files were modified in current session git status --porcelain # Get detailed changes git diff git diff --cached -
Analyze the current conversation context:
- Review what work was just completed in this chat session
- Identify if a specific plan was being followed
- Note any tests that were run and their results
- Track any problems encountered during implementation
-
Search for associated plan document:
- If plan reference was provided as $1, use that
- Otherwise, look in
.strategic-claude-basic/plan/for recent plans - Check conversation context for plan references
- Look at file changes to infer what feature was being worked on
-
Determine summary scope:
Found uncommitted changes in [N] files. Based on the session context, I can see you were working on: [brief description] [If plan found]: This appears to be implementing Plan: [plan filename] [If no plan]: This appears to be standalone implementation work I'll create a summary focusing on problems and incomplete work from this session. Proceeding with summary generation...
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 · 298 lines · 10 tokens per session scan A c10280847a02
summarize is a command published in the GitHub repository Fomo-Driven-Development/strategic-claude-base (2 stars, last pushed 9mo ago), licensed MIT. It adds 10 tokens to every session and 2,135 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 2026-08-31.
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.