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/forsonny/maker-framework/makergit clone --depth 1 https://github.com/forsonny/maker-frameworkWhat 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 | $0.00015 | $0.00635 |
| Opus 5 | $0.00008 | $0.00318 |
| Sonnet 5 | $0.00003 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
maker 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAKER Pipeline Command
Execute the full MAKER (Massively Decomposed Agentic Processes) pipeline.
CRITICAL: Orchestration Only
YOU (the orchestrator) MUST NOT write, edit, or execute files directly.
All file operations MUST happen through the maker-solver subagent. Your role is STRICTLY to:
- Invoke subagents via the Task tool
- Pass state between steps
- Handle validation and retry logic
- Report progress
FORBIDDEN ACTIONS for the orchestrator:
- Using Write tool directly
- Using Edit tool directly
- Using Bash for file operations
- Creating any files yourself
- Modifying any files yourself
If you find yourself about to write a file, STOP and invoke maker-solver instead.
Process
- Analyze the task: $ARGUMENTS
- Use Task tool with
subagent_type: "maker-framework:maker-complexity-estimator"to assess complexity - Use Task tool with
subagent_type: "maker-framework:maker-decomposition"to break into atomic steps - Use Task tool with
subagent_type: "maker-framework:maker-decomposition-discriminator"to validate - FOR EACH STEP in the decomposition:
a. Use Task tool with
subagent_type: "maker-framework:maker-solver"to execute the step b. Use Task tool withsubagent_type: "maker-framework:maker-red-flag"to validate output c. Retry up to 3x if flagged - For critical steps, use Task tool with
subagent_type: "maker-framework:maker-solution-discriminator"for voting - Use Task tool with
subagent_type: "maker-framework:maker-reviewer"for final validation - Loop back and fix any issues using maker-solver, NOT direct edits
Execution Rules
- Execute steps sequentially unless parallel opportunities identified
- Use maker-parallel-coordinator to identify parallelizable steps
- Create checkpoints after each successful step using maker-checkpoint-manager
- On failure, invoke maker-red-flag agent for analysis
- Cache successful patterns using maker-cache-manager for future use
- Loop back and fix any issues identified by maker-reviewer
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 · 72 lines · 15 tokens per session scan A dfb41ea5fd16
maker is a command published in the GitHub repository forsonny/maker-framework (7 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 635 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.