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 from-breaking-perspectivegit 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/from-breaking-perspective)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/from-breaking-perspective"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/from-breaking-perspective/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/from-breaking-perspective"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/from-breaking-perspective.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 | $0.00054 | $0.00552 |
| Opus 5 | $0.00027 | $0.00276 |
| Sonnet 5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
from-breaking-perspective 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- from-breaking-perspective — 92% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From breaking perspective
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants an answer only from the breaking seat (stakeholders, dependencies, accounting, compatibility under destructive pressure). |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Returns a breaking-perspective analysis in chat. |
| Done | Returns a breaking-perspective answer without blending. |
Inputs
The subject to analyze (a decision, design, change, or situation). Optional: the specific destructive pressure to apply (cost, removal, dependency failure, stakeholder withdrawal). Everything else is derived from the subject.
Procedure
- Identify the subject and the destructive pressure the user named. If the user named none, apply the full breaking seat: stakeholders, dependencies, accounting, and compatibility under destructive pressure. Done when: the subject and destructive pressure are identified, or the full seat is applied by default.
- Answer only from the breaking seat. Treat the subject as if the destructive pressure is actually applied: which stakeholders break, which dependencies fail, what the accounting shows under loss, and what stays compatible when parts are removed. Done when: the breaking-seat analysis covers stakeholders, dependencies, accounting, and compatibility.
- Do not blend other perspectives (business, codebase, impact, career, rent-seeking, innovation, stability, moat, human, skeptic) into the answer. Each lens answers only from its named seat; lenses are compared after their independent outputs, never mid-answer. Done when: no content from another lens appears in the answer.
- Stop when the breaking-seat analysis is complete. Do not recommend a decision or reconcile with other lenses; that is a later comparison step outside this skill. Done when: the analysis is complete with no recommendation or cross-lens reconciliation.
Failure and recovery
- Blended answer: if the output mixes another lens, restart from step 2 and remove the non-breaking content. The done predicate requires no blending.
- Missing subject: if no subject is supplied, ask for one. Do not invent a subject.
- No destructive pressure named and none derivable: apply the full breaking seat by default; this is not a failure.
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 · 35 lines · 54 tokens per session scan A 83d5d9ec3c05
from-breaking-perspective is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 54 tokens to every session and 552 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.