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 binutilsgit 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/binutils)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/binutils"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/binutils/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/binutils"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/binutils.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 | $0.01616 |
| Opus 5 | $0.00021 | $0.00808 |
| Sonnet 5 | $0.00008 | $0.00323 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
binutils 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GNU binutils
The GNU binutils manipulate existing binaries: static archives, symbol stripping, address to source mapping, and name demangling. Inspection of ELF structure belongs to elf-inspection.
Contract
| Field | Bound contract |
|---|---|
| Trigger | The task creates or modifies a static archive, strips or converts a binary, separates debug info, maps a crash address to source, extracts printable strings, or demangles a symbol. |
| Authority | Reversible local: writes only the archive, binary, or debug files the user names, and preserves each input when producing a new output file; rollback is version control or the preserved input. No remote mutation. |
| Side effect | Local writes to archives, binaries, .debug files, and generated object files. Local reads of every other file. |
| Done | The named artifact exists with the requested transformation applied, verified by re-running the matching inspection command (ar t, file, addr2line, nm -C) on the output. |
Inputs
- The target file or files: required. Name every input; the skill writes only named targets.
- The transformation: required. Create, strip, convert, debuglink, embed, map, or demangle.
- The target architecture: required for cross targets, so the tool prefix is
aarch64-linux-gnu-orarm-none-eabi-instead of the host tools.
Procedure
- Build a static archive with
ar.rinserts,ccreates without a warning,swrites the symbol index. Done when:ar tlists the expected members andnm libfoo.ashows their symbols.
ar rcs libfoo.a foo.o bar.o baz.o
ar t libfoo.a # list members
ar x libfoo.a foo.o # extract one member
ar r libfoo.a new.o # insert or replace
ar d libfoo.a old.o # delete
ranlib libfoo.a # rebuild the index after an external edit
LTO objects carry GIMPLE IR that plain ar indexes incorrectly. Use gcc-ar and gcc-ranlib for GCC, or llvm-ar for Clang.
- Strip a binary. Choose the flag from what must survive. Done when:
file progreportsstripped(or not) as intended, and the symbols that must remain do.
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 · 121 lines · 42 tokens per session scan A 1870a556ae7d
binutils 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 1,616 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".
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.
optimize
Use when asked to optimize code, speed up a path, reduce allocations, repair a regression, or profile a target. Not for remote, credential, publish, deploy, or irreversible changes.
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.