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 skills add sjarmak/coding-agent-workflows --skill research-projectgit clone --depth 1 https://github.com/sjarmak/coding-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/coding-agent-workflows/research-project)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/research-project"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/research-project/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/skills/sjarmak/coding-agent-workflows/research-project"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/research-project.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 | $0.00023 | $0.00396 |
| Opus 5.5 | $0.00009 | $0.00158 |
| Sonnet 5.5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
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 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.
What it actually says
Research Project: Diverge → Converge → Premortem
Run the complete PRD creation pipeline as a single invocation. This chains three skills in sequence, passing outputs between them.
Arguments
[N] "research question or topic"
- N is the agent count for the diverge stage (default 3).
- The topic is the research question or feature to investigate.
Execution
Step 1: Diverge
Invoke the /diverge skill with the provided arguments. This spawns N independent research agents and produces a PRD.
Wait for the PRD file to be created (format: prd_{slugified_topic}.md).
Step 2: Converge
Invoke the /converge skill, passing the PRD file path from Step 1.
This runs a structured debate to refine the PRD and resolve tensions.
Step 3: Premortem
Invoke the /premortem skill, passing the refined PRD from Step 2.
This runs prospective failure analysis and annotates the PRD with risks and mitigations.
Output
Present the final risk-annotated PRD path and a brief summary:
- Key decisions from convergence
- Top 3 risks from premortem
- Recommended next step (usually
/prd-build <prd-path>)
Rules
- Do NOT ask questions between steps, flow continuously
- Do NOT skip steps, all three must run
- If a step fails, report the error and stop (do not proceed with incomplete input)
- Each step produces files, pass file paths, not inline content
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 · 53 lines · 23 tokens per session scan A 718c0041f842
research-project is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 396 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 2026-08-31.
Other skills, from other repositories
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
kimi-webbridge
A way for an AI agent to control the user's real web browser, including pages where the user is already signed in. It can navigate, click, type, read page content, and take screenshots.