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 differential-security-reviewgit 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/differential-security-review)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/differential-security-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/differential-security-review/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/differential-security-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/differential-security-review.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 | $0.02401 |
| Opus 5 | $0.00032 | $0.01201 |
| Sonnet 5 | $0.00013 | $0.00480 |
| Haiku 4.5 | $0.00006 | $0.00240 |
Grade A, and why
differential-security-review 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Differential security review
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user supplies a pull request, commit, diff, or baseline comparison and asks for security regressions, blast radius, changed-code test gaps, or adversarial review. |
| Authority | Reversible-local: read changed and baseline code plus Git history, optionally delegate high-risk attacker modeling to a subagent, and write one differential review report. No VCS mutation, credential, paid, published, deployed, or remote mutation. |
| Side effect | A local markdown report file; repository code and Git history are read only. |
| Done | Every in-scope change is risk-classified at the declared depth and the report records evidence-backed findings, test gaps, blast radius, historical context, concrete exploit paths where warranted, limitations, and a recommendation. |
Inputs
- Target (required): PR URL, commit SHA, or diff path.
- Baseline (optional):
--baseline <ref>comparison reference; defaults to the merge base or parent commit. - Depth (optional): an explicit quick-triage request from the user narrows scope and the user accepts the residual risk; otherwise full depth applies.
Procedure
Prioritize risk and use evidence. Focus on auth, crypto, external calls, value transfer, and validation removal. Back every finding with Git history, line numbers, and attack scenarios. Adapt the depth to the codebase size. State coverage limits and confidence plainly. Always write the report file.
Rationalizations that must not be skipped
| Rationalization | Why it is wrong | Required action |
|---|---|---|
| "Small PR, quick review" | Heartbleed was 2 lines | Classify by RISK, not size |
| "I know this codebase" | Familiarity breeds blind spots | Build explicit baseline context |
| "Git history takes too long" | History reveals regressions | Never skip the historical analysis step |
| "Blast radius is obvious" | Transitive callers get missed | Calculate it quantitatively |
| "No tests = not my problem" | Missing tests elevate risk | Flag in report, elevate severity |
| "Just a refactor, no security impact" | Refactors break invariants | Analyze as HIGH until proven LOW |
| "I'll explain verbally" | No artifact = findings lost | Always write the report file |
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 · 120 lines · 64 tokens per session scan A 4009a6176229
differential-security-review 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 2,401 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
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
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".
gate-and-merge
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.
doubt-driven
Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.
pr-review-canvas-html
Use when asked to render a GitHub PR as a standalone review HTML page. Fetches PR data via gh API, renders diffs with move detection, and serves the artifact on a local port. Not for Cursor Canvas output — use pr-review-canvas.
review
Use when asked to review a pull request, examine code changes, find bugs, or audit a branch. Standard mode produces a severity-graded validated-findings report with concrete fixes; depth mode fans out parallel bug/security and quality reviewers and synthesizes a unified verdict. Not for an iterative review-and-fix…