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 batteryshark/rekit --skill r2-recongit clone --depth 1 https://github.com/batteryshark/rekitWrote 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/batteryshark/rekit/r2-recon)<a href="https://agentmods.dev/skills/batteryshark/rekit/r2-recon"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/r2-recon.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 | $0.00143 | $0.00789 |
| Opus 5 | $0.00072 | $0.00394 |
| Sonnet 5 | $0.00029 | $0.00158 |
| Haiku 4.5 | $0.00014 | $0.00079 |
Grade A, and why
r2-recon 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 8d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
radare2 Recon
Cross-format static recon of a native binary with radare2.
When to use
Use this for a cross-format pass over a native executable or library (ELF / PE /
Mach-O / DEX / …) that connects analyzed functions, entry points, and decoded strings,
including UTF-16. Start with bin-triage when the format is unknown; pair the result
with native-decompile (rizin pdg) to read interesting functions.
What it does
Opens one r2 headless session (-q -e scr.color=0 -c …), runs analysis
(aaa by default; --analysis none for a fast structural-only pass), and dumps
every JSON command (ij, iSj, iij, iEj, iej, aflj, izj) separated
by ?e echo markers — the runner splits on the markers and json.loads each
chunk, so a shape difference on one command degrades quietly instead of failing
the whole skill. Sections get per-section entropy computed from the file bytes
(the packed/compressed signal). Imports are classified by capability across
both Windows (VirtualAlloc, CreateProcess, …) and POSIX (execve, ptrace,
dlopen, socket …). Strings are scanned for URLs / IPs / paths / shell /
exec-API indicators. Emits BINARY.* atoms shared with pe/elf/macho-analyze
and bin-triage.
Prerequisites
- python3 (runner) and
r2(radare2) on PATH. radare2 is a large native toolchain, so it is not bundled — install viabrew install radare2(macOS),apt install radare2(Debian/Ubuntu), from https://radare.org, orr2pm. Until it's present,doctormarks the skill not-ready andrunreports the honest gap.
Usage
rekit run r2-recon ./suspicious.elf # human-readable + atoms
rekit run r2-recon ./unknown --format json | jq . # machine result
rekit run r2-recon ./huge.bin --analysis none # fast, structural only
Notes
- r2 auto-detects the format, so this is the one skill for "I have a native
blob of unknown format" —
pe/elf/macho-analyzestay preferable when you know the format and want their format-specific atoms (TLS callbacks, RELRO, …). - This is a batch skill: one stateless pass that emits a JSON result + atoms.
To go deeper on a specific function, pair it with
native-decompile(rizinpdg) — recon here, decompile there.
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.
- 8d ago First seen · 55 lines · 143 tokens per session scan A d80c709ea03a
r2-recon is a skill published in the GitHub repository batteryshark/rekit (10 stars, last pushed 29d ago), licensed Apache-2.0. It adds 143 tokens to every session and 789 once invoked, about $0.0007 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.