Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/smallnest/goal-workflownpx agentmods add skills/smallnest/goal-workflow/graphWrote 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/smallnest/goal-workflow/graph)<a href="https://agentmods.dev/skills/smallnest/goal-workflow/graph"><img src="https://agentmods.dev/badge/skills/smallnest/goal-workflow/graph/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/smallnest/goal-workflow/graph"><img src="https://agentmods.dev/badge/skills/smallnest/goal-workflow/graph.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 | $0.00129 | $0.04085 |
| Opus 5.5 | $0.00052 | $0.01634 |
| Sonnet 5.5 | $0.00026 | $0.00817 |
| Haiku 4.5 | $0.00013 | $0.00409 |
Grade A, and why
graph 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 1mo 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.
This is a copy
98% identical to graph — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graph — Task/PRD to Parallel Execution Graph
Turn a task (or PRD / SPEC / issue set) into a directed acyclic graph of work units, layer it into supersteps (waves), and implement each wave's independent nodes concurrently using subagents. Each node runs the full /goal → /review-it → /ship-it pipeline inside its own git worktree, so parallel nodes never clobber each other's working tree. Between waves, a fan-in barrier merges results and re-plans the next wave.
This is the parallel sibling of /loop-it. /loop-it is strictly sequential (one worktree, one issue at a time). /graph fans out every independent node in a wave at once.
Mental Model (borrowed from LangGraph / graph engineering)
| Concept | Here |
|---|---|
| Node | One implementable unit of work (an issue / subtask) |
| Edge | A dependency: B depends on A → edge A → B |
| Superstep / wave | A set of nodes whose deps are all satisfied — run concurrently |
| Fan-out | Dispatch one subagent per node in the current wave |
| Fan-in (barrier) | Wait for all nodes in the wave before starting the next |
| State channel | .graph_state — shared checkpoint, rewritten between waves (resume source) |
| Live tracker | graph.html — Claude-style light-theme dashboard, re-rendered from .graph_state at every checkpoint |
| Dynamic re-plan | After a wave, revise the graph if new work/deps emerged |
Core principle: Independent nodes in the same wave have no shared state and no ordering dependency, so they can run in true parallel. Dependencies define the only ordering. Everything else runs at once.
Overview
Input (task / PRD / SPEC / issues)
│
▼
1. Decompose into nodes ─────────► nodes = {id, title, deps, criteria, scope}
│
▼
2. Build DAG + validate ─────────► detect cycles, orphan deps
│
▼
3. Topological layering ─────────► waves = [[n1,n2,n3], [n4,n5], [n6]]
│
▼
4. Render graph + confirm with user
│
▼ (write .graph_state + graph.html — open graph.html to watch live)
┌──────────── per wave (superstep) ────────────┐
│ │
│ FAN-OUT: 1 subagent per node (parallel) │
│ each subagent, in its own git worktree: │
│ /goal (inline implement) → /review-it │
│ → /ship-it │
│ │
│ FAN-IN barrier: wait for ALL nodes │
│ integrate, update .graph_state │
│ re-render graph.html │
│ re-plan next wave if graph changed │
│ │
└───────────────────────────────────────────────┘
│
▼
All waves done → final summary
What ships with it
1 file 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.
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.
- 1mo ago First seen · 330 lines · 129 tokens per session scan A 787a3694c019
graph is a skill published in the GitHub repository smallnest/goal-workflow (293 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 4,085 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to graph, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
maintaining-agent-context
You MUST use this when creating, auditing, optimizing, or maintaining repository agent instructions - AGENTS.md, CLAUDE.md, .claude/rules/, and instruction-related SKILL.md content - covering context architecture, always-loaded context cost, stale, duplicated, or conflicting instructions, and keeping agent memory…
negafix
You MUST use this when writing or substantively editing prose in a project (docs, READMEs, marketing copy) and when asked to audit, score, or clean up negative parallelism, the "it's not just X, it's Y" construction. Not for ordinary factual negation.
debugging
You MUST use this when investigating bugs, regressions, failing tests, build or integration failures, flaky behavior, performance anomalies, or other unexpected technical behavior.
parallel-agents
You MUST use this when several units of work might run concurrently through agents - independent investigations, specialist reviews, repository analyses, or plan tasks that look unrelated - covering whether they are genuinely independent, which mutable state needs isolation, how wide the wave should be, and how…
review-resolution
You MUST use this when code-review findings, PR comments, CI review output, or reviewer suggestions need technical validation before any fix or disposition, including feedback from human reviewers, subagents, GitHub, static-analysis tools, or external review systems.
verification-gate
You MUST use this when work is about to be called complete, done, fixed, ready, or mergeable - before a completion claim, a merge or pull request, a branch finish, or a handoff report.