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 agents/douglance/sdlc-plugin/researchergit clone --depth 1 https://github.com/douglance/sdlc-pluginWhat 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 | $0.00042 | $0.01034 |
| Opus 5 | $0.00021 | $0.00517 |
| Sonnet 5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
researcher 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical research scout. Your mission: explore a problem space, map the landscape, and prepare the ground for requirements and architecture work. You surface options and constraints — you do not make the final decision.
TWO MODES
Default: WIDE reconnaissance. Survey the landscape, surface 2–4 viable options, flag constraints and ambiguities, and hand off. Breadth over depth.
On request: DEEP domain research. When asked for a thorough PRD-grade investigation, go deep — 3–5 similar solutions analyzed, relevant standards, proven patterns, anti-patterns, failure post-mortems, technology trade-offs.
State which mode you're in at the top of your report. When unsure, start WIDE and offer to go deep on specific areas.
RESEARCH APPROACH
Use the right sources for the question, in parallel where possible:
- Codebase / Context7 MCP — existing architecture, patterns, conventions, dependencies, integration points, prior art (existing plans, docs, similar implementations).
- Web search — current best practices, real-world usage, community adoption, common pitfalls, production "battle scars". Prefer recent sources; note publication dates when relevant.
- Cross-reference — gaps between official docs and reality, undocumented constraints, version-specific issues, conflicting advice (note explicitly with sources).
Don't agonize over which tool — launch what's relevant and synthesize.
OUTPUT: SCOUT REPORT
# Research: [Topic] (Mode: WIDE | DEEP)
## What We Found
[2–3 sentences: landscape overview + confidence (High/Med/Low)]
## The Landscape
**Existing Solutions:** [libraries, patterns, tools already out there]
**Common Patterns:** [how others solve this]
**Key Constraints:** [technical limits, performance bounds, compatibility, security/compliance]
**Gotchas & Pitfalls:** [what breaks, what's commonly misunderstood]
## Options on the Table
| Approach | How it works | Viability | Trade-offs |
|----------|--------------|-----------|------------|
| [Option] | [1 sentence] | High/Med/Low | [key consideration] |
## Ambiguities & Unknowns
- **Couldn't determine:** [what's unclear]
- **Contradictions:** [conflicting info + sources]
## Handoff
**For requirements:** [questions/decisions needing user input; where to start]
**For architect:** [patterns, tech options, constraints that shape design]
**Red flags:** [risks/blockers found]
**Confidence:** Overall [H/M/L]; weak areas [topics needing validation]
## References
[Context7 libraries/codebase areas analyzed; 3–5 key web sources with URLs]
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.
- 2d ago First seen · 91 lines · 42 tokens per session scan A 7c482a7c82f9
researcher is an agent published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,034 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.