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 divergegit 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/diverge)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/diverge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/diverge/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/diverge"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/diverge.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 | $0.00037 | $0.00624 |
| Opus 5 | $0.00018 | $0.00312 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
diverge 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diverge
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants to expand a decision field. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output: an expanded decision field. |
| Done | The decision field is expanded with additional options and dimensions. |
Inputs
- A decision question or statement (required): the choice the user is weighing.
- Known options (optional): candidate choices already on the table.
- Known dimensions (optional): criteria or axes already being considered.
- Constraints or context (optional): bounds, preferences, or stakes that shape the field.
Procedure
- Restate the decision question in one sentence and confirm it names a choice between alternatives, not a task to execute. If it does not name a choice, stop and ask the user to restate it. Done when: a choice between alternatives is confirmed or the skill stops to ask.
- List the known options and known dimensions the user supplied; mark any that are absent as empty. Done when: the known sets are listed or marked empty.
- Generate additional options the user has not named, including opposites, hybrids, deferrals, and status-quo variants. Each option is one phrase plus a one-line rationale. Done when: new options are generated without duplicates.
- Generate additional dimensions the user has not named: criteria or axes along which any option could be evaluated. Each dimension is one phrase plus a one-line description of what it measures. Done when: new dimensions are generated without duplicates.
- Tag every option and dimension as known or new so the expansion is visible. Done when: every entry is tagged.
- Return the expanded field as a structured list: decision question, options (known then new), dimensions (known then new). Done when: the ordered structured list is returned.
Failure and recovery
- Vague decision question: ask the user to restate it as a choice between alternatives before expanding; do not invent the question.
- No known options or dimensions supplied: proceed with an empty known set and generate the field from the question alone; note that the starting set was empty.
- Expansion produces no new options or dimensions: report that the field appears saturated and return the known set unchanged rather than padding with redundant entries.
- Partial result: return whatever options and dimensions were generated, label the set as partial, and state that generation stopped early; never claim the field is complete.
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 53256f537831
- 5d ago First seen · 41 lines · 37 tokens per session scan A 3927a0de837b
diverge is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 624 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.