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 attack-shapegit 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/attack-shape)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/attack-shape"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/attack-shape/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/attack-shape"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/attack-shape.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 | $0.00034 | $0.01053 |
| Opus 5.5 | $0.00014 | $0.00421 |
| Sonnet 5.5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
attack-shape 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 1mo 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:
- attack-shape — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack shape
Contract
| Field | Bound contract |
|---|---|
| Trigger | User wants adversarial stress-testing of an architecture, structure, or shape. Either the agent attacks and the human defends, or the agent proposes and the human attacks. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. The agent emits chat output only. |
| Side effect | An attack or proposal transcript in chat, plus the surviving or broken shape recorded in chat. |
| Done | The shape has been attacked from both directions, the human has defended or attacked, and the surviving shape (or non-converged record) is recorded. |
Inputs
The proposed architecture, structure, or shape to test. The human must supply it as text, a diagram description, or a reference to an artifact already in context. Without it the skill stops.
Optional: named attack axes the human wants prioritized (coupling, abstraction depth, failure modes, scalability, ownership boundaries).
Optional: a scope limit naming what is out of bounds for the attack.
Optional: constraints, scale, existing components, and non-goals for a proposal round.
A human participant must be present; the skill does not converge without one.
Procedure
-
Restate the target shape from the supplied input and confirm scope with the human before attacking or proposing. Do not test material outside the stated scope. Done when: the shape is restated and scope is confirmed.
-
Determine the direction. If the human supplied a shape to attack, the agent attacks and the human defends. If the human asked the agent to propose, the agent proposes and the human attacks. Done when: the direction is set and the first move is made.
-
Enumerate the attack axes relevant to the shape: coupling between parts, abstraction depth versus leakage, failure and recovery paths, scalability and growth pressure, ownership and boundary clarity, plus any named axes the human supplied. Done when: all relevant axes are enumerated.
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.
- 1mo ago Changed · -33 tokens per session cc98eb588a15
- 1mo ago First seen · 66 lines · 67 tokens per session scan A 144617ce75b4
attack-shape is a skill published in the GitHub repository OutlineDriven/outline-driven-development (53 stars, last pushed 22d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,053 once invoked, about $0.0001 per session on Opus 5.5. 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".
optimize
Use when asked to optimize code, make a path faster, make this as fast as possible, reduce allocations, repair a regression, profile a target, grill every inefficiency, or run a subsystem or repo-wide performance campaign against a measured floor; when a performance requirement, slowness report, Core Web Vitals miss…
debug
Hypothesis-driven debugging. Use when a test fails, a crash or exception occurs, output is wrong, or an intermittent flake has no obvious cause.
ios-build-fix
Use when asked to run /ios-build-fix to fix a failing iOS build, regenerate an Xcode project from project.yml, or correct UI behavior. Not for a clean rebuild: use ios-build-cleanup.
strike-the-root
Use when a bug, failure, flake, regression, review finding, or ticket needs the core fixed so it cannot recur. Not for greenfield features: use tdd. Not for style-only review or typo-class one-liners.
extremely-optimize
Use when asked to run a performance campaign against a measured floor. Not for hypothesis-only analysis without mutation: use fastopt.