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.
git clone --depth 1 https://github.com/allisoneer/agentic_auxilaryWrote 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/allisoneer/agentic_auxilary/create_plan_init)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/create_plan_init"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/create_plan_init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/create_plan_init"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/create_plan_init.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01460 |
| Opus 5.5 | $0.00007 | $0.00584 |
| Sonnet 5.5 | $0.00004 | $0.00292 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
create_plan_init 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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<workflow_contract>
- Follow all 5 steps in order.
- Read every user-provided file or document fully before broader investigation.
- Summarize your understanding in 2-3 sentences and confirm with the user before deeper investigation.
- Use
todowritein Step 2 and keep exactly one itemin_progress. - Prefer
tools_ask_agentfor discovery and subsystem analysis; use the main agent for orchestration, synthesis, and user interaction. - In Step 3, call
tools_ask_reasoning_modelwithprompt_type="reasoning"to resolve gaps and get recommendations. - Do not pretend unresolved questions are settled; ask the user when a decision is required.
- Do not proceed to final planning until all critical blockers are resolved or explicitly accepted by the user. </workflow_contract>
MAKE SURE you follow ALL 5 steps in order. Track your progress with todowrite throughout.
<step_1>
Step 1: Gather Task Context
- Infer the concrete planning target from
<userMessage>. - If the user referenced files, tickets, research documents, or prior artifacts, read each one fully before doing anything else.
- Summarize your understanding in 2-3 sentences and confirm with the user.
- If there is still no clear task after reading the supplied context, ask one clarification question and stop.
- Stop after the confirmation request in Step 3. Do not call
tools_thoughts_list_documents,tools_thoughts_list_references, or launch deeper investigation until the user confirms or corrects your understanding.
</step_1>
<step_2>
Step 2: Spawn Parallel Agents
The research document passed into this command contains file:line references and findings. Use these to inform your agent strategy—the research already identified key files and areas.
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.
- 1mo ago First seen · 142 lines · 18 tokens per session scan A b0efff3b9f3e
create_plan_init is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 1,460 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-08.
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.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.