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 OutlineDriven/outline-driven-development --skill compile-3d-workflowgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/compile-3d-workflow)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/compile-3d-workflow"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/compile-3d-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/outlinedriven/outline-driven-development/compile-3d-workflow"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/compile-3d-workflow.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 | $0.00040 | $0.00921 |
| Opus 5 | $0.00020 | $0.00461 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
compile-3d-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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compile 3D workflow
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user asks for direction and a compilable 3D workflow from an interview. |
| Authority | Reversible local: writes only the named local 3D workflow artifact file; rollback is deleting that file. No remote mutation. |
| Side effect | Writes one local 3D workflow artifact file. |
| Done | A validated local 3D workflow artifact file exists and passes every structural check. |
Inputs
- A direction interview with the user, supplying: the problem being solved, what success looks like, binding constraints, and what is explicitly out of scope. All four required; none inferred.
- The output file path for the workflow artifact. Required.
Artifact schema
The workflow artifact is a YAML file with this structure:
problem: <string>
success_criteria: <string>
constraints: [<string>, ...]
out_of_scope: [<string>, ...]
topology:
nodes:
- id: <string>
task: <string>
depends_on: [<node_id>, ...]
ontology:
groups:
- name: <string>
members: [<node_id>, ...]
feedback_loops:
- name: <string>
sensor: <string>
comparator: <string>
actuator: <string>
Every node id referenced in depends_on must exist in nodes. Every node id in ontology group members must exist in nodes. Every feedback loop must name a sensor, comparator, and actuator as non-empty strings.
Procedure
- Conduct the direction interview. Ask the user for the problem, success criteria, binding constraints, and explicit out-of-scope. Record the answers verbatim. Done when: all four interview inputs are recorded verbatim, or the missing input is named and the skill stops.
- Author the workflow artifact from the interview answers. Build the three dimensions:
- Topology: a DAG of tasks. Each node has an id, a task description, and a depends_on list naming the node ids it waits on. No cycles. No node depends on itself. Every depends_on entry must reference an existing node id.
- Ontology groups: named concept clusters classifying the work domains. Each group names its member node ids. Every group is non-empty. Every member must exist in the topology.
- Feedback loops: cybernetic control cycles. Each loop names its sensor (what is measured), comparator (what is expected), and actuator (what action re-routes). All three are non-empty strings. Done when: the artifact combines all three dimensions from the interview answers.
- Validate the artifact against the schema. Check every rule:
- Every node has a unique id and a non-empty task.
- Every depends_on entry references an existing node id.
- No cycle exists in the dependency graph (topological sort succeeds).
- Every ontology group is non-empty and every member references an existing node id.
- Every feedback loop names a non-empty sensor, comparator, and actuator. Done when: every check passes, or the specific defect is named and the skill stops.
- Write the validated artifact to the output file path as YAML. State the rollback path: delete the local artifact file. No remote state was touched. Done when: the artifact file is written and the rollback path is stated.
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.
- 2d ago Changed · -19 tokens per session 9c214d7c4ae9
- 4d ago First seen · 75 lines · 59 tokens per session scan A bb79b580758a
compile-3d-workflow is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 921 once invoked, about $0.0002 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
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.