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 constant-time-analysisgit 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/constant-time-analysis)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/constant-time-analysis"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/constant-time-analysis.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 | $0.00040 | $0.03120 |
| Opus 5 | $0.00020 | $0.01560 |
| Sonnet 5 | $0.00008 | $0.00624 |
| Haiku 4.5 | $0.00004 | $0.00312 |
Grade A, and why
constant-time-analysis 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constant-time analysis
Contract
| Field | Bound contract |
|---|---|
| Trigger | User needs static inspection of compiled assembly or VM bytecode for secret-dependent variable-time operations, or runtime and statistical evidence that a cryptographic implementation leaks timing information. |
| Authority | Reversible local: static mode is read-only and produces only local intermediate compiler output, discarded after analysis; runtime mode writes only a timing-test harness, its compiled binary, and measured sample files under a scratch directory, and rollback is deleting the scratch directory and compiled artifacts. The implementation under test is read and compiled but never edited. No remote mutation. |
| Side effect | A compiler or bytecode analyzer report read from local toolchain output (static), or a local timing-test harness and measured runtime samples (runtime). |
| Done | Static mode: the analyzer runs with warnings for every configuration in the target matrix and every reported instruction is traced to secret or public data before verdict. Runtime mode: a runtime test reports calibrated evidence of leakage or a bounded inconclusive result, with the exercised configuration named. |
Inputs
- Mode: one of
static(default) orruntime. Runtime mode fires when the user needs empirical timing evidence rather than inspection of emitted instructions. - Source file or directory to analyze (required).
- Target language, inferred from file extension or supplied (required).
- Configuration matrix for native languages (C, C++, Go, Rust, Swift): an explicit list of target architectures and optimization levels to sweep. Each entry names one architecture (
x86_64,arm64,riscv64, ...) and one optimization level (O0throughO3,Os,Oz). At minimum two architectures and two optimization levels including one size-optimized level (OsorOz). Required for native languages; not applicable to JVM/CIL or interpreted languages. - Optional: function-name regex to narrow scope; compiler override (
gcc,clang,go,rustc,swiftc). - Runtime mode also requires: the cryptographic function or binary to test, and a statement of which inputs are secret (private keys, exponents, nonces, password hashes) versus public.
- Runtime mode optional: the compiler and flags used in production (default tests at the production optimization level, e.g.
-O3 -march=native), the target CPU architecture, and a measurement budget in minutes.
What ships with it
2 files 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 · +38 lines · -34 tokens per session a763a5db0a72
- 3d ago First seen · 102 lines · 74 tokens per session scan A 4250232df42d
constant-time-analysis is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 3,120 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
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…