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 binary-hardeninggit 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/binary-hardening)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/binary-hardening"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/binary-hardening/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/binary-hardening"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/binary-hardening.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 | $0.00049 | $0.02042 |
| Opus 5 | $0.00024 | $0.01021 |
| Sonnet 5 | $0.00010 | $0.00408 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
binary-hardening 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binary hardening
Contract
| Field | Bound contract |
|---|---|
| Trigger | Hardening an ELF binary or its build: checksec analysis, RELRO, PIE, stack canaries, FORTIFY_SOURCE, CET and shadow stack, Clang CFI, AArch64 BTI and PAC, MTE, or seccomp syscall filtering. |
| Authority | Read-only. The skill emits flags, commands, and analysis; it writes no files. Nothing to roll back. No remote mutation. |
| Side effect | Hardening flag sets, verification commands, and a protection report per binary. |
| Done | The binary's current mitigations are measured, the missing ones have concrete flags, and each flag is confirmed supported by the project's compiler and libc. |
Inputs
- Binary or build (required): the ELF to check, or the build to harden.
- Toolchain (required):
gcc --versionorclang --version,ld --version, andldd --versionfor the libc. Grounded channels: GCC 16.x, Clang 23.1.0, binutils 2.47, glibc 2.44. - Target platforms (optional): x86-64, AArch64, or both.
- Threat scope (optional): which mitigations the deployment actually needs.
Procedure
- Measure the binary first:
checksec --file=./mybinary
checksec --dir=/usr/bin
| Protection | Good | Concern |
|---|---|---|
| RELRO | Full RELRO | Partial or none |
| Stack canary | Canary found | None |
| NX | NX enabled | Disabled |
| PIE | PIE enabled | None |
| FORTIFY | Yes | No |
Done when: every row has a measured value for the binary. 2. Apply the hardening flag set that the toolchain supports:
CFLAGS="-O2 -pipe \
-fstack-protector-strong \
-fstack-clash-protection \
-fcf-protection \
-D_FORTIFY_SOURCE=3 \
-D_GLIBCXX_ASSERTIONS \
-fPIE \
-Wformat -Wformat-security -Werror=format-security"
LDFLAGS="-pie \
-Wl,-z,relro \
-Wl,-z,now \
-Wl,-z,noexecstack \
-Wl,-z,separate-code"
gcc ${CFLAGS} -o prog main.c ${LDFLAGS}
Shared libraries compile with -fPIC instead of -fPIE and link with -shared. Gate each flag on the toolchain: _FORTIFY_SOURCE=3 needs GCC 12 or newer, or Clang 9 or newer, plus glibc 2.34 or newer headers; older toolchains fall back to level 2. Done when: the build compiles clean and checksec shows the new values.
3. Read what each mitigation buys:
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.
- 3d ago First seen · 126 lines · 49 tokens per session scan A 98892982d025
binary-hardening is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,042 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 2026-09-06.
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".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
snippet-image-rendering
Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.