GSD Pi is a command-line coding agent and project workflow system that plans, implements, verifies, and tracks software work through milestones, tasks, Git worktrees, and stored project notes. It is for developers who want structured, longer-running agent sessions using different model providers. The catalogue entries extend GSD Pi with skills and agents.
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-pi --skill api-designgit clone --depth 1 https://github.com/open-gsd/gsd-piWrote 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-pi/api-design)<a href="https://agentmods.dev/skills/open-gsd/gsd-pi/api-design"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-pi/api-design/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-pi/api-design"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-pi/api-design.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 | $0.00091 | $0.02076 |
| Opus 5.5 | $0.00036 | $0.00830 |
| Sonnet 5.5 | $0.00018 | $0.00415 |
| Haiku 4.5 | $0.00009 | $0.00208 |
Grade A, and why
api-design 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 15d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invocation points:
- Adding a new public API endpoint
- Redesigning an internal API boundary between services
- Code review of a PR that introduces HTTP handlers
- A slice whose acceptance criteria include "the API works"
- A GraphQL schema change
<core_principle> CALLERS OUTLIVE YOUR ASSUMPTIONS. An API you ship today has to keep working when your internals change, when the mobile app version two is still in use, and when a third party integrates against it. Design for extension, not just for the current caller.
HONEST STATUS CODES. 200 OK with {"error": "not found"} is a lie. 404 says not found. Use the HTTP semantics the protocol offers — HTTP clients, caches, and intermediaries rely on them.
PAGINATION IS NON-OPTIONAL. Any list endpoint that doesn't paginate will eventually get a request for "all records" that kills your database. </core_principle>
Step 1: Gather the contract
Answer, or ask (one round, 1–3 questions):
- Who are the callers? Internal service / mobile app / public third-party / same-repo frontend.
- What's the versioning stance? None / URL-path (
/v1/) / header-based / GraphQL schema evolution. - Auth model? Public / API key / OAuth / session cookie / mTLS / none-but-internal-only.
- Idempotency expectation? Is a retry safe? Required?
- Consistency model? Read-your-writes, eventual, serializable?
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.
- 15d ago Changed 7b0bda16e5c3
- 18d ago Changed · +2 lines b5ffb297dc92
- 1mo ago First seen · 191 lines · 91 tokens per session scan A 8915bda09a99
api-design is a skill published in the GitHub repository open-gsd/gsd-pi (1,326 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,076 once invoked, about $0.0004 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-graphify
Build, query, and inspect the project knowledge graph in .planning/graphs/.
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
gsd-mempalace-recall
Recall decisions, patterns, and surprises from MemPalace before planning.
gsd-quick-batch
Batch several /gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-surface
Toggle which skills are surfaced — apply a profile, list, or disable a cluster without reinstall.