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 breaking-drivengit 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/breaking-driven)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/breaking-driven"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/breaking-driven.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.01322 |
| Opus 5 | $0.00023 | $0.00661 |
| Sonnet 5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
breaking-driven 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking-driven development
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user says "this module is bloated", "rewrite this properly", or "break it and rebuild". |
| Authority | Reversible local: writes only VCS-tracked targets (destructive changes; show the exact set before mutation); rollback is version control. No remote mutation. |
| Side effect | Deletes obsolete implementation and residue, writes the replacement, and adds essential-behavior tests. |
| Done | Consumer contract preserved, every divergence classified, residue absent, and verifier green. |
Inputs
A named path or identified target must be supplied or named in the request and defines the whole job. Optionally, a blank invocation or explicit repo-wide wording surveys the repo and works through a ranked list one target at a time.
Procedure
-
Pick the target. A named path goes straight to step 2. Survey only on explicit repo-wide intent, ranking candidates by bloat signal, size, duplication, indirection depth, branch density, then work the list in order. Any identifiable target scopes to itself; escalating a named grievance into a whole-tree campaign is this skill's worst failure, and trigger phrasing alone cannot tell a single target from a sweep. Done when: a single target is selected or a ranked survey list is produced on explicit repo-wide intent.
-
Classify the surface. Inventory consumers. Mark interior (every caller in-tree, nothing persisted or shipped) or boundary (public API, wire or on-disk format, config running in someone else's deployment, plugin point, anything a version was promised against). Interior is a conclusion, not a default: every consumer channel static analysis cannot resolve, reflection, string dispatch, generated code, external integrations, operator runbooks, carries boundary class until evidence or an explicit yes moves it. An empty grep over dynamic dispatch is not evidence; unresolved means boundary. Done when: every consumer is classified interior or boundary with evidence for interior claims.
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.
- yesterday Changed · -18 tokens per session 861181b9e362
- 4d ago First seen · 46 lines · 63 tokens per session scan A 44215612849f
breaking-driven is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,322 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
test-auto-fix
Diagnoses failing tests across any project, classifies each failure as a test-bug, prod-bug, or unsure, confidence-gates the fix (auto-apply at >=90%, 80-89 ask, <80 escalate), applies it, and re-runs until green. Surface-driven: reads per-project configuration from a surface file keyed by normalised git remote URL.…
toolchain-health
Use when the user runs /toolchain-health and wants a trustworthy green/yellow/red verdict on the installed toolchain with ranked repairs. Not for tasks that require source or remote-system changes.
bug-fix
Fix bugs with regression prevention using test-first approach.
fixing-flaky-tests
Diagnose and fix flaky tests. Covers race conditions, timing issues, test pollution, async leaks.
dx-step-fix
Diagnose and fix a blocked step — compilation error, test failure, or review rejection. Tries direct fix first; if that fails, creates corrective steps in implement.md (heal). Use when /dx-step reports a failure.
debug-issue
Structured workflow for debugging a reported or reproduced issue. Use when the user asks to debug a bug, find root cause, or fix a failing scenario.