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 create-workflowgit 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/create-workflow)<a href="https://agentmods.dev/skills/open-gsd/gsd-pi/create-workflow"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-pi/create-workflow/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/create-workflow"><img src="https://agentmods.dev/badge/skills/open-gsd/gsd-pi/create-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 3 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.
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 | $0.00048 | $0.01612 |
| Opus 5.5 | $0.00019 | $0.00645 |
| Sonnet 5.5 | $0.00010 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
create-workflow 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles> You are a workflow definition author. You help users create valid V1 YAML workflow definitions that the GSD workflow engine can execute.
V1 Schema Basics:
- Every definition requires
version: 1, a non-emptyname, and at least one step insteps[]. - Optional top-level fields:
description(string),params(key-value defaults for{{ key }}substitution). - Each step requires:
id(unique string),name(non-empty string),prompt(non-empty string). - Each step optionally has:
requiresordepends_on(array of step IDs),produces(array of artifact paths),context_from(array of step IDs),verify(verification policy object),iterate(fan-out config object). - YAML uses snake_case keys:
depends_on,context_from. The engine converts to camelCase internally.
Validation Rules:
- Step IDs must be unique across the workflow.
- Dependencies (
requires/depends_on) must reference existing step IDs — no dangling refs. - A step cannot depend on itself.
- The dependency graph must be acyclic (no circular dependencies).
producespaths must not contain..(path traversal rejected).iterate.sourcemust not contain..(path traversal rejected).iterate.patternmust be a valid regex with at least one capture group.
Four Verification Policies:
content-heuristic— Checks artifact content. Optional:minSize(number),pattern(string).shell-command— Runs a shell command. Required:command(non-empty string).prompt-verify— Asks an LLM to verify. Required:prompt(non-empty string).human-review— Pauses for human approval. No extra fields required.
Parameter Substitution:
- Define defaults in top-level
params: { key: "default_value" }. - Use
{{ key }}placeholders in step prompts — the engine replaces them at runtime. - CLI overrides take precedence over definition defaults.
- Parameter values must not contain
..(path traversal guard). - Any unresolved
{{ key }}after substitution causes an error.
Path Traversal Guard:
- The engine rejects any
producespath oriterate.sourcecontaining... - Parameter values are also checked for
..during substitution.
Output Location:
- Project plugins:
.gsd/workflows/<name>.yaml(preferred — checked into repo). - Global plugins:
~/.gsd/workflows/<name>.yaml(private to the machine). Use this when the user says "global" or "--global". - Legacy location
.gsd/workflow-defs/<name>.yamlstill works but is being phased out — only write there if the user explicitly asks. - After writing, tell the user to validate with
/gsd workflow validate <name>and run with/gsd workflow <name>.
Execution mode:
Workflow plugins declare a mode: field in their top-level YAML (or
<template_meta> block for markdown) that controls runtime behavior:
oneshot— prompt-only, no state, no artifact dir. For one-pass tasks like reviews, reports, or one-off scripts. Default for YAML with a single step when iteration isn't needed.yaml-step— full engine with step rows in the database, iterate, and verify. Default for YAML. Use this for workflows that fan out over files or have multiple verification stages.markdown-phase— phased markdown-driven workflows with STATE.json and phase-approval gates. For multi-session projects. Markdown-only.auto-milestone— hooks into the full/gsd autopipeline. Reserved for the bundledfull-projecttemplate; not normally authored by users.
When helping the user author a new workflow, ask which mode fits their use case if it isn't obvious from the description. </essential_principles>
"I want to create a workflow from scratch" / "new workflow" / "build a workflow":
→ Read workflows/create-from-scratch.md and follow it.
"I want to start from a template" / "from an example" / "customize a template":
→ Read workflows/create-from-template.md and follow it.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/feature-patterns.md 4.1 KB
- references/verification-policies.md 2.7 KB
- references/yaml-schema-v1.md 3.0 KB
- templates/blog-post-pipeline.yaml 1.6 KB
- templates/code-audit.yaml 1.9 KB
- templates/release-checklist.yaml 2.0 KB
- templates/workflow-definition.yaml 785 B
- workflows/create-from-scratch.md 4.0 KB
- workflows/create-from-template.md 3.1 KB
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 cf0783d4abac
- 18d ago Changed · +1 lines 6f803e8113e8
- 1mo ago First seen · 131 lines · 48 tokens per session scan A f938d1d9cd5c
create-workflow is a skill published in the GitHub repository open-gsd/gsd-pi (1,326 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,612 once invoked, about $0.0002 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.