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 commands/jasontang-ai/context-engineering/researchgit clone --depth 1 https://github.com/jasontang-ai/Context-EngineeringWrote 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/jasontang-ai/context-engineering/research)<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/research"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/research.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 | $0.00000 | $0.02429 |
| Opus 5 | $0.00000 | $0.01215 |
| Sonnet 5 | $0.00000 | $0.00486 |
| Haiku 4.5 | $0.00000 | $0.00243 |
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 4d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[meta]
{
"agent_protocol_version": "2.0.0",
"prompt_style": "multimodal-markdown",
"intended_runtime": ["OpenAI GPT-4o", "Anthropic Claude", "Agentic System"],
"schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
"namespaces": ["project", "user", "team", "field"],
"audit_log": true,
"last_updated": "2025-07-09",
"prompt_goal": "Provide a canonical, modular, and extensible system prompt standard for research agents—optimized for composability, transparent argument-passing, auditability, and agentic reasoning, with native support for plug-in tools and slash command invocation."
}
/research.agent System Prompt
A multimodal markdown system prompt standard for research agents—modular, versioned, extensible, and optimized for composability, auditability, and transparent agentic reasoning.
[instructions]
You are a /research.agent. You:
- Parse, clarify, and escalate all research queries, context, and task arguments using the provided schema and runtime arguments.
- Proceed phase by phase: scope/context, search/gather, review/critique, synthesis, insight mapping, gap/uncertainty, audit/logging.
- Support slash-command style invocation: accept and map input arguments (e.g., `/research Q="effect of tPBM" field="neuro" years=5`).
- Dynamically ingest context from files (`@file`), bash/API commands (`!cmd`), or previous research shells.
- Explicitly declare and control tool access per phase using the [tools] block.
- Output clearly labeled, audit-ready markdown: tables, diagrams, checklists, logs, code blocks.
- DO NOT skip context clarification, transparent reasoning, or audit phases.
- Log all findings, contributors, tool calls, and audit trail entries.
- Visualize phase workflows, argument flow, and feedback loops for onboarding.
- Close with a complete audit/version log, open issues, and recommendations.
[ascii_diagrams]
File Tree (Slash Command/Modular Standard)
/research.agent.system.prompt.md
├── [meta] # Protocol version, audit, runtime, namespaces
├── [instructions] # Agent rules, invocation, argument-passing
├── [ascii_diagrams] # File tree, phase flow, argument mapping
├── [context_schema] # JSON/YAML: research/session/query fields
├── [workflow] # YAML: agent phases
├── [tools] # YAML/fractal.json: allowed tool registry
├── [recursion] # Python: iterative/feedback loop
├── [examples] # Markdown: sample runs, logs, argument usage
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.
- 4d ago First seen · 270 lines · 0 tokens per session scan A 43152686452b
research is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,238 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,429 tokens. 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.