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-plan-phasegit 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-plan-phase)<a href="https://agentmods.dev/skills/open-gsd/gsd-core/gsd-plan-phase"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-core/gsd-plan-phase/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-plan-phase"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-core/gsd-plan-phase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 7 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00016 | $0.01215 |
| Opus 5 | $0.00008 | $0.00607 |
| Sonnet 5 | $0.00003 | $0.00243 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade A, and why
gsd-plan-phase 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default flow: Research (if needed) → Plan → Verify → Done
Research-only mode (--research-phase <N>): Spawn gsd-phase-researcher for phase N, write RESEARCH.md, then exit before the planner runs. Useful for cross-phase research, doc review before committing to a planning approach, and correction-without-replanning loops where iterating on research alone is dramatically cheaper than re-spawning the planner. Replaces the deleted research-phase command (#3042).
Research-only modifiers:
- No flag — when
RESEARCH.mdalready exists, auto-uses it: emits a one-line notice and exits cleanly, no prompt. --research— force-refresh: re-spawn the researcher unconditionally, no prompt. Bypasses the existing-RESEARCH.md auto-use path.--view— view-only: print existingRESEARCH.mdto stdout. Does not spawn the researcher. Cheapest mode for the correction-without-replanning loop. If noRESEARCH.mdexists yet, errors with a hint to drop--view.
Orchestrator role: Parse arguments, validate phase, research domain (unless skipped), spawn gsd-planner, verify with gsd-plan-checker, iterate until pass or max iterations, present results.
<execution_context>
@/.claude/gsd-core/workflows/plan-phase.md
@/.claude/gsd-core/references/ui-brand.md
</execution_context>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. Do not skip questioning steps because AskUserQuestion appears unavailable; use vscode_askquestions instead.
</runtime_note>
Flags:
--research— Force re-research even if RESEARCH.md exists--skip-research— Skip research, go straight to planning--gaps— Gap closure mode (reads VERIFICATION.md, skips research)--skip-verify— Skip verification loop--prd <file>— Use a PRD/acceptance criteria file instead of discuss-phase. Parses requirements into CONTEXT.md automatically. Skips discuss-phase entirely.--ingest <path-or-glob>— Use one or more ADR files instead of discuss-phase. Parses locked decisions + scope fences into CONTEXT.md automatically. Skips discuss-phase entirely.--ingest-format <auto|nygard|madr|narrative>— Optional ADR parser format override (autodefault).--reviews— Replan incorporating cross-AI review feedback from REVIEWS.md (produced by/gsd-review)--text— Use plain-text numbered lists instead of TUI menus (required for/rcremote sessions)--mvp— MVP enrichment on top of the default tracer-first ordering: frames the phase goal as a user story and, on Phase 1 of a new project, also emitsSKELETON.md(Walking Skeleton). Vertical slicing itself is now the default (see--no-tracer);--mvpno longer turns it on. Can be persisted on a phase via**Mode:** mvpin ROADMAP.md.--no-tracer— Opt out of the default tracer-first decomposition and plan horizontal layers (the legacy default). By default every plan LEADS with one production-quality end-to-endtracerslice that is verified before any expansion task.--no-reversibility-gates— Suppress the human checkpoint that a one-way-door decision normally earns, for runs you intend to leave unattended. By default a decision ratedone-way(undo needs a migration, breaks a published contract, or is impossible) gets acheckpoint:decisionbefore the task implementing it. Ratings are still recorded on tasks andcostlyitems still flagged — the flag changes what stops the run, not what the plan remembers.
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.
- 7d ago First seen · 65 lines · 16 tokens per session scan A 4ae27cbd263d
gsd-plan-phase is a skill published in the GitHub repository open-gsd/gsd-core (9,319 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,215 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".
gsd-orchestrator
Build software products autonomously via GSD headless mode. Handles the full lifecycle: write a spec, launch a build, poll for completion, handle blockers, track costs, and verify the result. Use when asked to "build something", "create a project", "run gsd", "check build status", or any task that requires autonomous…
gsd-headless
Orchestrate GSD (Git Ship Done) projects programmatically via headless CLI. Use when an agent needs to create milestones from specs, execute dev workflows, monitor progress, check status, or control execution (pause/stop/skip/steer). Triggers on "run gsd", "create milestone", "execute project", "check gsd status"…
api-design
Design or review an HTTP/REST/GraphQL API for versioning, pagination, error shapes, idempotency, auth, status codes, cache headers, and breaking-change management. Use when asked to "design an API", "shape the endpoints", "design the schema", "add a new endpoint", "review this API", or when building/modifying a public…
forensics
Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via .gsd/ activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash"…