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/evansims/openfga-mcp/explore-plan-code-testgit clone --depth 1 https://github.com/evansims/openfga-mcpWhat 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 | $0.00000 | $0.00504 |
| Opus 5 | $0.00000 | $0.00252 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
explore-plan-code-test 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
At the end of this message, I will ask you to do something. Please follow the "Explore, Plan, Code, Test" workflow when you start.
Explore
First, use parallel subagents to find and read all files that may be useful for implementing the ticket, either as examples or as edit targets. The subagents should return relevant file paths, and any other info that may be useful.
Plan
Next, think hard and write up a detailed implementation plan. Don't forget to include tests, lookbook components, and documentation. Use your judgement as to what is necessary, given the standards of this repo.
If there are things you are not sure about, use parallel subagents to do some web research. They should only return useful information, no noise.
If there are things you still do not understand or questions you have for the user, pause here to ask them before continuing.
Break up large tasks into smaller subtasks. This way, we can update this plan as we go and mark tasks as completed as we implement them later.
Save this implementation plan to a file called PLAN.md in the root of the project directory.
Code
When you have a thorough implementation plan, you are ready to start writing code. Follow the style of the existing codebase (e.g. we prefer clearly named variables and methods to extensive comments). Make sure to run our autoformatting script when you're done, and fix linter warnings that seem reasonable to you.
Update the PLAN.md file incrementally as each step is implemented, so the plan persists across sessions and can be resumed at any time.
Test
Use parallel subagents to run tests, and make sure they all pass.
If your changes touch the UX in a major way, use the browser to make sure that everything works correctly. Make a list of what to test for, and use a subagent for this step.
If your testing shows problems, go back to the planning stage and ultrathink.
Write up your work
When you are happy with your work, write up a short report that could be used as the PR description. Include what you set out to do, the choices you made with their brief justification, and any commands you ran in the process that may be useful for future developers to know about.
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 · 40 lines · 0 tokens per session scan A 53f4ce276c06
explore-plan-code-test is a command published in the GitHub repository evansims/openfga-mcp (10 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 504 tokens. 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
validate-dependencies
Validate all task dependencies for issues.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
flow-nexus-auth
Flow Nexus authentication and user management.
validate-prd
Validate an existing PRD against BMAD standards - comprehensive review for completeness, clarity, and quality.
editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension.
add-tool
Scaffold a new FreeAgent MCP tool (handler + registration + test) following the repo pattern.