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 c-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/c-security-review)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/c-security-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/c-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/c-security-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/c-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 | $0.00042 | $0.02924 |
| Opus 5 | $0.00021 | $0.01462 |
| Sonnet 5 | $0.00008 | $0.00585 |
| Haiku 4.5 | $0.00004 | $0.00292 |
Grade A, and why
c-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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C security review
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user requests a complete userspace C or C++ security review with an explicit threat model, severity filter, and model. |
| Authority | Reversible local: write only the .c-review-results/<stamp>/ run directory under the current working directory. Roll back by deleting that directory. No remote mutation. |
| Side effect | A .c-review-results/<iso-timestamp>/ directory holding units.json, ledger.json, findings.json, REPORT.md, and REPORT.sarif. The reviewed tree is never modified. |
| Done | Every unit in scope has a ledger row per question or is named as uncovered, every reported finding carries a validation verdict of confirmed or needs-context, refuted findings are removed with their count disclosed, and REPORT.md and REPORT.sarif agree. |
Inputs
Required, resolved before review. Infer from free text on the invocation ("remote" to REMOTE, "local" to LOCAL_UNPRIVILEGED, "all" or "high only" to the filter, an explicit model name, "X only" to scope_subpath), then ask once for whatever stays unresolved. Never silently default a required parameter.
threat_model:REMOTE,LOCAL_UNPRIVILEGED, orBOTH. Scopes which bug classes count and the severity table each finding is scored against.worker_model: the model for every review pass. An explicit name, orinheritfor the session model.severity_filter:all,medium, orhigh. What reaches REPORT.md and REPORT.sarif.
Optional:
scope_subpath(default.): repo-relative directory. A finding must live inside it, and it is the tree the unit list is built from.context_roots(default.): directories read freely for callers, build flags, and reachability. Narrow it toscope_subpathonly when the user forbids wider reading, and state that reachability confidence drops.
Scope is native userspace C and C++: memory safety, integer overflow, races, type confusion, daemons, and services. Kernel drivers and modules, bare-metal or embedded code with no libc, and managed languages are out of scope. Stop and say so when the target is one of those.
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.
- 2d ago Changed · +22 lines · -25 tokens per session d10822ca8794
- 5d ago First seen · 62 lines · 67 tokens per session scan A d3b331b85728
c-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 42 tokens to every session and 2,924 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
bounded-model-checking-c
Use when C or C++ code needs memory-safety or undefined-behavior guarantees proved with CBMC, or ACSL contracts checked with Frama-C Eva or WP. Not for choosing the proof policy: use proof-driven.
cpp-modules
C++20 modules skill for modern C++ projects. Use when working with named modules, module partitions, header units, CMake MODULESOURCES, Clang -fmodules-ts, BMI caching issues, or migrating from headers to modules. Activates on queries about C++20 modules, import statements, module interface units, header units, or BMI…
openmp
OpenMP skill for shared-memory parallel programming. Use when writing parallel for loops, reductions, task parallelism, SIMD directives, GPU offloading, or profiling with Score-P/TAU. Activates on queries about OpenMP, pragma omp, schedule static dynamic, reduction, false sharing, or OMPNUMTHREADS.
xmake-targets
Use when configuring targets in xmake.lua — setting kind (binary/static/shared), adding files/includes/links, defining dependencies between targets, and applying per-target compile/link flags.
cpp
Use when writing modern C++ (17/20/23). Covers RAII, smart-pointer ownership, move semantics, ranges, concepts, and eliminating undefined behavior with sanitizers.
arduino-code-generator
Generate Arduino and embedded C++ snippets for sensors, actuators, buses, state machines, timing, data logging, and hardware abstraction. Use when a user requests implementation code and provide the exact board, framework, toolchain, pins, voltage, memory, and library versions first. Bundled templates target UNO…