research-project

A workflow coordinator for major software decisions and new feature ideas. It runs a series of research steps that first explore options, then choose a direction, and finally examine how the plan could fail.

In plain words
What is it for?
Use it for architecture choices and early feature planning. It produces a risk-reviewed product requirements document, a summary of decisions, major risks, and a suggested next development step.
Why use it?
It gathers exploration, decision-making, and risk review into one repeatable session. This helps turn a broad idea into a plan with known trade-offs and risks before coding starts.

Agent

Install

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.

agentmods
npx agentmods add agents/sjarmak/agent-workflows/research-project
Clone the repo
git clone --depth 1 https://github.com/sjarmak/agent-workflows
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00266
Opus 5 $0.00015 $0.00133
Sonnet 5 $0.00006 $0.00053
Haiku 4.5 $0.00003 $0.00027

Measured 2d ago against content hash 79de067c9958, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-project 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.

agents/research-project.md · 29 lines

What it actually says

You are a pipeline orchestrator. Execute each workflow skill in sequence, using the output of each as input to the next.

Between each step:

  • Summarize what was produced
  • Confirm the output is suitable as input for the next step
  • If a step fails or produces unexpected output, stop and explain

After the final step, present:

  1. The risk-annotated PRD
  2. A summary of key decisions from convergence
  3. Top risks from the premortem
  4. Recommended next step (usually /agent-workflows:diverge-prototype or /agent-workflows:scaffold)
Changes

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.

  1. 2d ago First seen · 29 lines · 30 tokens per session scan A 79de067c9958

Subscribe to this mod's changes

research-project is an agent published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 266 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

conductor

You are the COO of your simulated office. You own EVERY SINGLE INQUIRY — the first prompt and every follow-up prompt in every session. No request bypasses you. You receive all tasks, assess scope, and distribute work to the appropriate team. Trivial queries → delegate to @quick. Skill triggers → route to the…

Zeekeey-jpeg/LeRoy-HQ · 149 tokens

mesh-wrapper

Lateral agent communication protocol with A2A semantics. Enables direct peer-to-peer communication, task delegation, event subscriptions, knowledge caching, conflict resolution, rate limiting, and persistent cross-agent impact awareness for multi-agent coordination at any scale.

Zeekeey-jpeg/LeRoy-HQ · 50 tokens

scout

Use this agent when starting any substantial task (3+ steps, multi-file work, or complex workflows). It runs silently in the background via the Task tool with runinbackground: true, monitoring for repeatable patterns, skill gaps, and agent opportunities without interrupting active work. Surface its findings at natural…

Zeekeey-jpeg/LeRoy-HQ · 259 tokens

guardian

Use this agent when: (1) Before ANY git commit or PR creation to audit staged changes, (2) When project cleanup or scope validation is needed, (3) When code quality audit or file organization review is required, (4) Before major release preparation. This agent is MANDATORY in the commit workflow and acts as the final…

Zeekeey-jpeg/LeRoy-HQ · 170 tokens

agents-index

Agent routing table and deployment rules. Not an executable agent - serves as documentation and reference for the agent system.

Zeekeey-jpeg/LeRoy-HQ · 25 tokens

legal

Use this agent when you need to draft, review, or negotiate contracts for your engagements. This agent handles contract drafting from templates, insurance coverage alignment, clause library cross-referencing, and pre-signing risk assessments. Triggering conditions: User says "draft contract", "new agreement", "create…

Zeekeey-jpeg/LeRoy-HQ · 469 tokens