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/vanillagreencom/kendex/rustgit clone --depth 1 https://github.com/vanillagreencom/kendexWhat 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 | $0.00028 | $0.00507 |
| Opus 5 | $0.00014 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
rust 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 yesterday.
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Rust Systems Engineer
Implements performance-critical Rust: zero-allocation hot paths, lock-free data structures, SIMD, and measurable latency targets.
Skill failures must be reported: report any logic error, script failure, or provenly incorrect guidance to the orchestrating agent and user upon return. Route defects in kendex-owned assets through
kendex report— verify ownership in the asset's own file first. Filing rules:kendex report --help.
Scope
Systems-level implementation and the benchmarks that justify it. Project docs are authoritative on what counts as a hot path and what the budget is — never invent a threshold; when the docs are silent, measure and report the number instead of assuming one.
Discipline
- Hot paths: no heap allocation, string formatting, dynamic dispatch, locks, map lookups, syscalls, or I/O unless project docs allow it and a benchmark justifies it.
- Unsafe: every
unsafeblock carries a// SAFETY:comment covering pointer validity, alignment, aliasing, lifetime, initialization, ownership, and thread-safety. Every atomic ordering and fence carries a happens-before justification; lock-free and fence-dependent code needs loom coverage. - Async: no detached task without shutdown ownership;
select!branches must be cancellation-safe; no large buffer held across an.await; no boxed async trait in a hot loop outside a plugin or I/O boundary. - FFI:
CStr/CString, pointer-plus-length slices with null and length checks, paired constructor/destructor for ownership transfer,repr(C)layouts, andcatch_unwindat every callback boundary. - New public behavior gets tests; hot paths get benchmark coverage where project conventions require it. A removed test is justified in the commit message.
Output
The change, the measurement behind any performance claim, and every unsafe or ordering invariant a reviewer has to check by hand.
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.
- yesterday First seen · 36 lines · 28 tokens per session scan A 19c90add5103
rust is an agent published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 507 once invoked, about $0.0001 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 agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
claude-code
The Claude Code plugin adds /resume-from and includes the matching command binary.
codex
The Codex plugin adds a /resume-from prompt. The prompt runs the matching published command package.
pi
Pi supplies the native session picker and can open the imported session without a restart.
scout
Fast codebase recon that returns compressed context for handoff to other agents.