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/gazmagik/claude-memory-plugin/thoughtgit clone --depth 1 https://github.com/GaZmagik/claude-memory-pluginWrote 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/gazmagik/claude-memory-plugin/thought)<a href="https://agentmods.dev/commands/gazmagik/claude-memory-plugin/thought"><img src="https://agentmods.dev/badge/commands/gazmagik/claude-memory-plugin/thought.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 | $0.00017 | $0.02232 |
| Opus 5 | $0.00009 | $0.01116 |
| Sonnet 5 | $0.00003 | $0.00446 |
| Haiku 4.5 | $0.00002 | $0.00223 |
Grade A, and why
thought 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 3d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Goal
Create a thinking document for structured deliberation on a topic, optionally invoking multiple agents with different output styles to gather diverse perspectives before concluding.
Prerequisites
CRITICAL: Before running any memory commands, you MUST activate the memory skill first using the Skill tool:
Skill: memory
This ensures the skill is loaded and the memory CLI command is available (installed via bun link). Without this step, the commands below may not work correctly.
Discovering Available Agents and Styles
To see which agents and output styles are available in your environment, run:
memory help think
This displays:
- AVAILABLE AGENTS: Domain experts like
curator,typescript-expert,security-code-expert, etc. - AVAILABLE OUTPUT STYLES: Personality styles like
Architect,Devils-Advocate,Pragmatist,Simplifier, etc.
Note: Available agents and styles vary by installation. Always check memory help think for your specific environment.
Execution Steps
1. Parse Arguments
Extract from $ARGUMENTS:
- topic (required): The deliberation topic (first positional argument or quoted string)
- --calls N (optional): Minimum number of agent calls to make before concluding (default: 0 = manual mode)
- --agents a1,a2 (optional): Comma-separated list of required agents to invoke
- --styles s1,s2 (optional): Comma-separated list of required styles to apply
Examples:
"Should we use Redis or PostgreSQL for caching?"
"API design for auth module" --calls 5 --agents typescript-expert,security-code-expert --styles Architect,Devils-Advocate
2. Create Thinking Document
memory think create "<topic>"
This creates a new thinking document and sets it as the current document for subsequent operations.
3. Add Initial Framing (Optional)
If the user provided context beyond just the topic, add an initial framing thought:
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.
- 3d ago First seen · 280 lines · 17 tokens per session scan A 39529c9eb8bc
thought is a command published in the GitHub repository GaZmagik/claude-memory-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 2,232 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.