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 framing-divergence-fanoutgit 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/framing-divergence-fanout)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/framing-divergence-fanout"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/framing-divergence-fanout/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/framing-divergence-fanout"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/framing-divergence-fanout.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 | $0.00064 | $0.00903 |
| Opus 5 | $0.00032 | $0.00451 |
| Sonnet 5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
framing-divergence-fanout 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 5d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framing divergence fanout
Contract
| Field | Bound contract |
|---|---|
| Trigger | User invokes a check that the current direction is tunnel-visioned or inherited its framing |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | None. Bounded fresh sub-sessions used only as inputs to classification. |
| Done | Bait stripped from the direction statement; every read classified incompatible/compatible/convergent; shared-root clustering complete; divergent-incompatible reads listed first; convergent reads labeled reassurance only; no consensus wording present. |
Inputs
- Direction of work (required): the current plan, approach, or framing the user wants stress-tested.
- Context (optional): background material that may inform the reads but must not constrain them to a single frame.
Procedure
- Strip bait. Remove leading, suggestive, or conclusory language from the direction statement. Restate it as a neutral description of what is being attempted and why, preserving the decision's substance without its rhetorical frame. Done when: the direction statement is restated in neutral terms with bait removed.
- Fan out 2-5 reads. Spawn between 2 and 5 independent sub-sessions. Each read examines the stripped direction from a distinct vantage point (e.g., opposing assumption, adjacent domain, historical failure mode, resource constraint, user-population segment). No read may copy or restate another. No majority vote, no averaging, no consensus synthesis across reads. Done when: 2 to 5 independent reads are spawned from distinct vantage points.
- Classify each read. Assign exactly one label to every completed read:
- Incompatible: the read identifies a framing flaw, hidden assumption, or outcome that contradicts the direction's intent.
- Compatible: the read accepts the direction's goal but proposes a meaningfully different path or emphasis.
- Convergent: the read independently arrives at the same framing as the direction. Done when: every completed read has exactly one classification label.
- Cluster by shared root. Group reads that share the same underlying assumption, evidence source, or structural concern. Label each cluster by its root. Reads with no shared root form single-member clusters. Done when: every read is assigned to a cluster with its root labeled.
- Order the report. List divergent-incompatible clusters first, then compatible clusters, then convergent clusters. Within each cluster, order by relevance to the direction's core claim. Done when: the report is ordered incompatible-first, compatible second, convergent last.
- Label convergence as reassurance. Every convergent read or cluster carries the explicit note: "Convergent = reassurance, not validation. It confirms the framing was inherited, not chosen." Do not use the words consensus, agreement, majority, or weight when describing the reads collectively. Done when: every convergent read carries the reassurance label and no consensus wording is present.
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.
- 5d ago First seen · 49 lines · 64 tokens per session scan A c0f1ba4a855f
framing-divergence-fanout is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 64 tokens to every session and 903 once invoked, about $0.0003 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.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.