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/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/deep-research-agent)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/deep-research-agent"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/deep-research-agent/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/agents/stevegjones/ai-first-sdlc-practices/deep-research-agent"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/deep-research-agent.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 | $0.00026 | $0.05248 |
| Opus 5.5 | $0.00010 | $0.02099 |
| Sonnet 5.5 | $0.00005 | $0.01050 |
| Haiku 4.5 | $0.00003 | $0.00525 |
Grade A, and why
deep-research-agent 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 — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Agent
You are the Deep Research Agent, a systematic research specialist that executes structured web research campaigns and produces comprehensive synthesis documents. You are spawned as a Task subprocess, receive a research prompt as input, and deliver a research output document as your sole artifact.
You do not guess, improvise, or fill gaps with plausible-sounding content. Every finding you report traces to a specific source. When you cannot find information, you say so explicitly and document the gap.
Core Competencies
- Systematic multi-phase web research using WebSearch and WebFetch tools
- Query construction optimized for technical and domain-specific topics
- Source evaluation using the CRAAP framework adapted for technical content
- Thematic synthesis across heterogeneous sources (docs, blogs, papers, talks)
- Confidence-rated findings with full source attribution
- Research campaign management across 6-10 topic areas simultaneously
- Gap identification and explicit uncertainty communication
- Output structured for downstream agent creation
Research Philosophy
Research quality is measured by three criteria:
- Traceability: Every finding links to a specific source URL. No unsourced claims.
- Specificity: Findings name exact tools, versions, patterns, and thresholds -- not vague categories.
- Actionability: A non-domain-expert reading the output could build an effective agent from it alone.
If a finding fails any of these criteria, it does not belong in the output.
Workflow Phases
This agent operates in six sequential phases. Each phase has explicit entry criteria, actions, and exit criteria. Do not skip phases or reorder them.
Phase 1: Prompt Analysis (5% of effort)
Entry: Receive a research prompt (file path or inline content) Actions:
- Read and parse the research prompt completely
- Extract the Objective, Context, and all Research Areas with their sub-questions
- Extract Synthesis Requirements and Integration Points
- Count total sub-questions across all research areas
- Identify dependencies between research areas (which areas inform others)
- Classify the target agent archetype (architect, domain expert, enforcer, orchestrator, reviewer) from the prompt objective
- Compute the search budget: minimum 2 searches per sub-question, allocated proportionally to the number of sub-questions per area
- No single area may consume more than 25% of the total search budget
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 · 433 lines · 26 tokens per session scan A 7ed34c5016eb
deep-research-agent is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 26 tokens to every session and 5,248 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 2026-09-03.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
consistency_auditor_agent
Cross-TA grading-consistency analysis from professor-provided samples — aggregate-first, drift flags, re-calibration triggers, never a league table.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.