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/research)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/research"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/research/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/research"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/research.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 | $0.01778 |
| Opus 5.5 | $0.00007 | $0.00711 |
| Sonnet 5.5 | $0.00004 | $0.00356 |
| Haiku 4.5 | $0.00002 | $0.00178 |
Grade A, and why
research 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<workflow_contract>
- Follow all 7 steps in order.
- Use
todowritestarting in Step 2, keep exactly one itemin_progress, and mark items complete immediately. This is your running session's execution checklist, not content for the research document. - Prefer
tools_ask_agentfor exploration; the main agent should synthesize rather than manually brute-force the codebase. - Do not write the research document until coverage is sufficient or remaining gaps are explicitly documented.
- If the request is too vague to research, ask a clarification question and stop there.
- Do not stop on intermediate agent output; keep iterating until the research is ready for handoff. </workflow_contract>
<step_1>
Step 1: Gather Context
- Infer the concrete research objective from
<userMessage>. - If the user named files, tickets, documents, or repositories, read each referenced file fully before doing anything else.
- If there is no concrete research target after reading the user input, ask one clarification question and wait.
- If the request is mostly clear but still has minor ambiguity, proceed with the best reasonable interpretation and state that assumption in your next user-facing update.
- Call
tools_thoughts_list_documents. - If Step 5 reveals relevant existing thoughts artifacts, note them for possible
tools_ask_agentcalls withlocation=thoughts. Do not read those documents directly in this step. - Call
tools_thoughts_list_referencesand note which references may matter.
</step_1>
<step_2>
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 · 161 lines · 18 tokens per session scan A 51d0b733fc84
research 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 1,778 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.