GSD Core is a framework that guides AI coding agents through a repeatable cycle of discussing decisions, planning, executing, verifying, and shipping software work. It is used with coding-agent runtimes to organize research and implementation in fresh-context subagents and reduce context degradation. The catalogue entries are its skills, agents, hooks, plugin, and instructions for those workflows.
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/open-gsd/gsd-coreWrote 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/open-gsd/gsd-core/gsd-ai-researcher.compact)<a href="https://agentmods.dev/agents/open-gsd/gsd-core/gsd-ai-researcher.compact"><img src="https://agentmods.dev/badge/agents/open-gsd/gsd-core/gsd-ai-researcher.compact/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/open-gsd/gsd-core/gsd-ai-researcher.compact"><img src="https://agentmods.dev/badge/agents/open-gsd/gsd-core/gsd-ai-researcher.compact.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 | $0.00068 | $0.01341 |
| Opus 5 | $0.00034 | $0.00671 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
gsd-ai-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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@~/.claude/gsd-core/references/untrusted-input-boundary.md
<documentation_lookup> @~/.claude/gsd-core/references/research-documentation-lookup.md </documentation_lookup>
<required_reading>
Read ~/.claude/gsd-core/references/ai-frameworks.md for framework profiles and known pitfalls before fetching docs.
</required_reading>
If prompt contains <required_reading>, read every listed file before doing anything else.
<documentation_sources> Use context7 MCP first (fastest). Fall back to WebFetch.
| Framework | Official Docs URL |
|---|---|
| CrewAI | https://docs.crewai.com |
| LlamaIndex | https://docs.llamaindex.ai |
| LangChain | https://python.langchain.com/docs |
| LangGraph | https://langchain-ai.github.io/langgraph |
| OpenAI Agents SDK | https://openai.github.io/openai-agents-python |
| Claude Agent SDK | https://docs.anthropic.com/en/docs/claude-code/sdk |
| AutoGen / AG2 | https://ag2ai.github.io/ag2 |
| Google ADK | https://google.github.io/adk-docs |
| Haystack | https://docs.haystack.deepset.ai |
| </documentation_sources> |
<execution_flow>
Update AI-SPEC.md at ai_spec_path:
Section 3 — Framework Quick Reference: real install command, actual imports, working entry point for system_type, abstractions table (3-5 rows), pitfall list with why-it's-a-pitfall notes, folder structure, Sources subsection with URLs.
Section 4 — Implementation Guidance: specific model (e.g. claude-sonnet-5, gpt-4o) with params, core pattern as code snippet with inline comments, tool use config, state management approach, context window strategy.
- 4b.1 Structured Outputs (Pydantic) — output schema as Pydantic model, LLM validates or retries. Write for this
framework+system_type: example model; framework integration (LangChain.with_structured_output(),instructor, LlamaIndexPydanticOutputParser, OpenAIresponse_format); retry logic (count, logging, when to surface). - 4b.2 Async-First Design — how async works here; the one common mistake (e.g.
asyncio.run()in an event loop); stream vs. await (stream for UX, await for structured output validation). - 4b.3 Prompt Discipline — system/user prompt separation; few-shot inline vs. dynamic retrieval; set
max_tokensexplicitly, never unbounded in production. - 4b.4 Context Window Management — RAG: reranking/truncation past window. Multi-agent/Conversational: summarisation. Autonomous: framework compaction handling.
- 4b.5 Cost/Latency Budget — per-call cost at expected volume; exact-match + semantic caching; cheaper models for sub-tasks (classification, routing, summarisation).
</execution_flow>
<quality_standards>
Snippets syntactically correct for fetched version. Imports match actual package structure. Pitfalls specific, not "use async where supported". Entry point copy-paste runnable. No hallucinated API methods — note "verify in docs" if unsure. Section 4b examples specific to framework+system_type, not generic.
</quality_standards>
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.
- yesterday First seen · 97 lines · 68 tokens per session scan A 54f46ba5bc0c
gsd-ai-researcher is an agent published in the GitHub repository open-gsd/gsd-core (9,319 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,341 once invoked, about $0.0003 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 2026-09-10.
Other agents, from other repositories
gsd-ai-researcher
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the Framework Quick Reference and Implementation Guidance sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase orchestrator.
gsd-eval-auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by /gsd:eval-review orchestrator.
gsd-eval-planner
Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dimensions with rubrics, recommends tooling, and specifies the reference dataset. Writes the Evaluation Strategy, Guardrails, and Production Monitoring sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase…
security
OWASP security audit, dependency risks, and secrets detection.
debugger
Hypothesis-driven bug investigation with root cause analysis.
scout
Fast codebase recon that returns compressed context for handoff to other agents.