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.
npx skills add open-gsd/gsd-core --skill gsd-audit-uatgit 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/skills/open-gsd/gsd-core/gsd-audit-uat)<a href="https://agentmods.dev/skills/open-gsd/gsd-core/gsd-audit-uat"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-core/gsd-audit-uat/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/open-gsd/gsd-core/gsd-audit-uat"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-core/gsd-audit-uat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00400 |
| Opus 5.5 | $0.00007 | $0.00160 |
| Sonnet 5.5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
gsd-audit-uat 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.
What it actually says
Invoke this Pi skill with /skill:gsd-audit-uat.
Pi dispatch (fail closed). Pi has no built-in subagent API; GSD provides the gsd_dispatch tool. Where a workflow step dispatches a named gsd-* role, call gsd_dispatch with role (the installed role name) and task (the full task text). A workflow that still writes the step as an Agent(...) call means the same: its subagent_type is the role and its prompt is the task. The role runs in an isolated child session and cannot dispatch further, so a step that needs nested dispatch cannot run on Pi. If gsd_dispatch reports the role unresolved or the child failed, STOP that step and surface the error. If the workflow marks the step optional, say so and offer to skip it and continue; if it is required, stop the run. Never execute the role's work inline as a substitute.
Pi includes. Pi does not expand @path references in a skill. Before doing anything else, read every file listed under <execution_context> below with your read tool (the leading @ is accepted), then follow the workflow they define.
<execution_context> @GSD_PI_ENGINE_ROOT/gsd-core/workflows/audit-uat.md </execution_context>
Scope: Glob: .planning/phases//-UAT.md Glob: .planning/phases//-VERIFICATION.md
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 Changed ad496e9c08f1
- 5d ago Changed · +1 lines 923dedd54cf4
- 1mo ago First seen · 26 lines · 18 tokens per session scan A cb5f445d66e7
gsd-audit-uat is a skill published in the GitHub repository open-gsd/gsd-core (10,857 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 400 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 2026-08-30.
Other skills, from other repositories
gsd-verify-work
Validate built features through conversational UAT.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
tdd
Test-driven development with red-green-refactor loops around vertical slices (tracer bullets), not horizontal layers. Use when asked to "use TDD", "write test-first", "red-green-refactor", "build this with tests", or when a feature has a clear observable contract. The discipline complement to the test/add-tests skills…
verify-before-complete
Block completion claims until verification evidence has been produced in the current message. Use before marking a task/slice/milestone complete, before creating a commit or PR, before saying "it works" or "tests pass", and any time you are about to claim work is done. The rule is: evidence before claims, always …
bmad-qa-generate-e2e-tests
Add end-to-end and API tests for features that already work, following the project's existing test harness. Use when the user asks for e2e tests, API tests, or automated coverage of an existing feature, or says "create qa automated tests for [feature]". Not for unit tests on work in flight, which the build writes.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.