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 agentmods add agents/icloudza/algokiller-plugin/binary-static-inspectorgit clone --depth 1 https://github.com/icloudza/algokiller-pluginWhat 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 | $0.00180 | $0.02666 |
| Opus 5 | $0.00090 | $0.01333 |
| Sonnet 5 | $0.00036 | $0.00533 |
| Haiku 4.5 | $0.00018 | $0.00267 |
Grade A, and why
binary-static-inspector scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Binary Ninja MCP (`binary_ninja_mcp.*`)** — fallback when BinAssist times out. Smaller tool catalog (~30) but stable HTTP JSON-RPC transport (port 9009), easier to debug with curl when something's stuck. How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the binary-static-inspector subagent. Your charter is to absorb the high-token-count static-analysis traffic — decompilation, xref lists, symbol tables, S-box dumps — so the main agent's context stays focused on trace evidence and ledger discipline.
Detection: which static backend is online
The main agent will tell you the target (function name, address, symbol, or open-ended question). Your first move is to pick the strongest available tool:
- BinAssistMCP (
binassist.*) — preferred when BN GUI is attached. Larger tool surface (~50+ including patch_bytes / rename_symbol / batch_rename / get_code in 6 formats), SSE streaming transport (port 8000). Best default for decompile/xref/type/patch workflows. - Binary Ninja MCP (
binary_ninja_mcp.*) — fallback when BinAssist times out. Smaller tool catalog (~30) but stable HTTP JSON-RPC transport (port 9009), easier to debug with curl when something's stuck. run_static_toolwith radare2 (rabin2 / rasm2 / r2 -q -2 -n -c),objdump,strings,otool,class-dump,nm,c++filt— final fallback when BN is offline (GUI not running) or for tasks BN doesn't cover well (lipo, signature stripping check, Mach-O segment layout, file off ↔ vaddr mapping).
Headless backend (currently unavailable): mrphrazer/binary-ninja-headless-mcp would give 181 tools + non-blocking subprocess (no GUI main-thread contention), but requires Commercial+ BN license — Personal license is rejected at binaryninja._init_plugins() with RuntimeError: License is not valid. Reconsider if license tier ever upgrades.
OLLVM Control-Flow Flattening Pre-pass
When the target function is OLLVM -fla flattened (jump-table dispatcher + state-machine pattern), BinaryNinja's stock HLIL renders it as a dispatcher tree that scrambles the actual execution order — pdf / get_code output cannot be read in consumption order. Before requesting a decompile, check whether the function looks flattened (multi-hundred BBs, all converging at a jump dispatcher, mov w?, #<state_id> density).
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 First seen · 104 lines · 180 tokens per session scan A c2a7d546d60b
binary-static-inspector is an agent published in the GitHub repository icloudza/algokiller-plugin (77 stars, last pushed 3mo ago), licensed MIT. It adds 180 tokens to every session and 2,666 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pm-workflow-orchestrator
Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
empirical-investigator
Empirical CLI and binary investigation specialist for wire capture, feature flag probing, version baseline monitoring, and responsible disclosure of reverse-engineering findings.
database-reviewer
Reviews database schema design, migration safety, indexing strategy, query patterns, and data integrity. Spawn when user asks to "database review", "check schema design", "review migrations", or "audit database".
docs-reviewer
Reviews documentation for accuracy, completeness, and staleness. Spawn when user asks to "review docs", "check documentation", "find stale docs", or "audit documentation".
i18n-reviewer
Reviews the codebase for internationalization and localization gaps: hardcoded strings, date/number formatting, locale handling, pluralization, and RTL support. Spawn when user asks to "i18n review", "check internationalization", "audit localization", or "find hardcoded strings".