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 skills/sjarmak/agent-workflows/research-projectnpx skills add sjarmak/agent-workflows --skill research-projectgit clone --depth 1 https://github.com/sjarmak/agent-workflowsWrote 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/skills/sjarmak/agent-workflows/research-project)<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/research-project"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/research-project.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00750 |
| Opus 5 | $0.00011 | $0.00375 |
| Sonnet 5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the complete PRD creation pipeline as a single invocation. Chains three skills in sequence — diverge (multi-perspective research), converge (structured debate), premortem (failure analysis) — passing file outputs between them. Produces a risk-annotated PRD ready for /prd-build or /scaffold.
Arguments
$ARGUMENTS — format: [N] "research question or topic" where N is optional agent count (default: 3)
Parse Arguments
Extract:
- agent_count: the optional leading integer (default 3, min 2, max 6)
- topic: the research question, feature description, or problem statement
If the topic is missing or unclear, ask the user to clarify before proceeding.
Phase 1: Diverge
Invoke the /diverge skill with the provided arguments. This spawns N independent research agents — each with a different lens (technical feasibility, user experience, risk/failure modes, prior art, first principles) — to explore the topic from uncorrelated perspectives.
Wait for the PRD file to be created (format: prd_{slugified_topic}.md).
The diverge output is a synthesis of all agent findings plus a draft PRD. Do NOT proceed until the file exists.
Phase 2: Converge
Invoke the /converge skill, passing the PRD file path from Phase 1.
This runs a structured debate: agents advocate competing positions from the diverge output, challenge each other's assumptions, propose compromises, and reach consensus. The result is a refined PRD with tensions resolved and trade-offs made explicit.
Wait for the convergence report and updated PRD.
Phase 3: Premortem
Invoke the /premortem skill, passing the refined PRD from Phase 2.
This spawns N agents who each write a narrative from the future where the project has failed — each for a different root cause (technical, operational, security, scope, organizational). Synthesizes into a risk registry with severity ratings and mitigations, then annotates the PRD with the top risks.
Wait for the risk-annotated PRD.
Phase 4: Present Results
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.
- 5d ago First seen · 67 lines · 22 tokens per session scan A 3d81a8cad972
research-project is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 750 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 skills, from other repositories
speckit.clarify
Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.
speckit.specify
Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.
release-docs
Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…
local-integration-testing
Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.
update-docs
Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…
docker-compose-first-install
Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.