Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/mohitmishra786/low-level-dev-skills/binutils)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/binutils"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/binutils.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00089 | $0.01336 |
| Opus 5 | $0.00044 | $0.00668 |
| Sonnet 5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GNU Binutils
Purpose
Guide agents through the binutils toolset for binary manipulation: static libraries, stripping, address-to-source mapping, and symbol demangling.
Triggers
- "How do I create a static library?"
- "How do I strip a binary but keep a debug file?"
- "I have an address from a crash — how do I find the source line?"
- "How do I demangle a C++ symbol name?"
- "How do I extract/replace sections in a binary?"
Workflow
1. ar — static library management
# Create static library
ar rcs libfoo.a foo.o bar.o baz.o
# List contents
ar t libfoo.a
# Extract an object
ar x libfoo.a foo.o
# Add/replace an object
ar r libfoo.a newbar.o
# Delete an object
ar d libfoo.a oldbar.o
# Show symbol index
nm libfoo.a
# Rebuild symbol index (after modifying archive externally)
ranlib libfoo.a
For LTO archives: use gcc-ar/gcc-ranlib or llvm-ar instead of plain ar.
2. strip — remove debug info
# Strip all debug info (reduce binary size)
strip --strip-all prog
# Strip only debug sections (keep symbol table)
strip --strip-debug prog
# Strip unneeded symbols (keep needed for linking)
strip --strip-unneeded prog
# In-place
strip prog
# To a new file
strip -o prog.stripped prog
3. objcopy — binary section manipulation
# Separate debug info from binary
objcopy --only-keep-debug prog prog.debug
objcopy --strip-debug prog
# Add debuglink (GDB finds prog.debug automatically)
objcopy --add-gnu-debuglink=prog.debug prog
# Convert binary to another format
objcopy -O binary prog prog.bin # raw binary (embedded)
objcopy -O srec prog prog.srec # Motorola S-record
# Add a section from a file
objcopy --add-section .resources=data.bin prog
# Remove a section
objcopy --remove-section .comment prog
# Change section flags
objcopy --set-section-flags .data=alloc,contents,load,readonly prog
# Embed a binary file as a symbol
objcopy -I binary -O elf64-x86-64 \
--rename-section .data=.rodata,alloc,load,readonly,data,contents \
data.bin data.o
# Then link data.o; access via _binary_data_bin_start / _binary_data_bin_end
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.
- 7d ago First seen · 179 lines · 89 tokens per session scan A 784397dacef9
binutils is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (195 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,336 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
debugging
Systematically diagnose and fix software bugs by analyzing error messages, stack traces, logs, and runtime behavior across multiple languages. Use when the user requests debugging or provides relevant inputs for this workflow.
log-analyzer
Parse agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and component-level error counts. Produces a structured anomaly report. Cron-compatible — silent if no issues, alert digest if anomalies found.
error-handler
Design error handling, structured logging, and observability with OpenTelemetry (traces, metrics, logs), error classification, recovery patterns (retry with jitter, circuit breaker, bulkhead, timeout), error budgets/SLOs with burn rate alerts, and production incident triage. Use when user asks to implement error…
performance-profiler
Performance profiling and optimization for web apps — Core Web Vitals (LCP, INP, CLS), Lighthouse audits, bundle analysis, backend profiling (CPU, memory, DB queries), N+1 detection, caching strategies (Redis, CDN, HTTP), and performance budgets. Use when user asks to improve performance, run Lighthouse audit, profile…
scientific-debugging
A method for debugging software by observing the problem, forming possible explanations, running small experiments, and then fixing and checking the result.
diagnosing-ml-failures
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance…