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/hyperledger-iroha/iroha/env_var_migrationgit clone --depth 1 https://github.com/hyperledger-iroha/irohaWrote 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/agents/hyperledger-iroha/iroha/env_var_migration)<a href="https://agentmods.dev/agents/hyperledger-iroha/iroha/env_var_migration"><img src="https://agentmods.dev/badge/agents/hyperledger-iroha/iroha/env_var_migration.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 | $0.00000 | $0.01532 |
| Opus 5 | $0.00000 | $0.00766 |
| Sonnet 5 | $0.00000 | $0.00306 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
env_var_migration 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 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Env → Config Migration Tracker
This tracker summarizes production-facing environment-variable toggles surfaced
by docs/source/agents/env_var_inventory.{json,md} and the intended migration
path into iroha_config (or explicit dev/test-only scoping).
Note: ci/check_env_config_surface.sh now fails when new production env
shims appear relative to AGENTS_BASE_REF unless ENV_CONFIG_GUARD_ALLOW=1 is
set; document intentional additions here before using the override.
Completed migrations
- IVM ABI opt-out — Removed
IVM_ALLOW_NON_V1_ABI; the compiler now rejects non-v1 ABIs unconditionally with a unit test guarding the error path. - IVM debug banner env shim — Dropped the
IVM_SUPPRESS_BANNERenv opt-out; banner suppression remains available via the programmatic setter. - IVM cache/sizing — Threaded cache/prover/GPU sizing through
iroha_config(pipeline.{cache_size,ivm_cache_max_decoded_ops,ivm_cache_max_bytes,ivm_prover_threads},accel.max_gpus) and removed runtime env shims. Hosts now callivm::ivm_cache::configure_limitsandivm::zk::set_prover_threads, tests useCacheLimitsGuardinstead of env overrides. - Connect queue root — Added
connect.queue.root(default:~/.iroha/connect) to the client config and threaded it through the CLI and JS diagnostics. JS helpers resolve the config (or an explicitrootDir) and only honourIROHA_CONNECT_QUEUE_ROOTin dev/test viaallowEnvOverride; templates document the knob so operators no longer need env overrides. - Izanami network opt-in — Added an explicit
allow_netCLI/config flag for the Izanami chaos tool; runs now requireallow_net=true/--allow-netand - IVM banner beep — Replaced the
IROHA_BEEPenv shim with config-drivenivm.banner.{show,beep}toggles (default: true/true). Startup banner/beep wiring now reads configuration only in production; dev/test builds still honour the env override for manual toggles. - DA spool override (tests only) — The
IROHA_DA_SPOOL_DIRoverride is now fenced behindcfg(test)helpers; production code always sources the spool path from configuration. - Crypto intrinsics — Replaced
IROHA_DISABLE_SM_INTRINSICS/IROHA_ENABLE_SM_INTRINSICSwith the config-drivencrypto.sm_intrinsicspolicy (auto/force-enable/force-disable) and removed theIROHA_SM_OPENSSL_PREVIEWguard. Hosts apply the policy at startup, benches/tests may opt in viaCRYPTO_SM_INTRINSICS, and the OpenSSL preview now respects only the config flag. Izanami already requires--allow-net/persisted config, and tests now rely on that knob rather than ambient env toggles. - FastPQ GPU tuning — Added
fastpq.metal.{max_in_flight,threadgroup_width,metal_trace,metal_debug_enum,metal_debug_fused}config knobs (defaults:None/None/false/false/false) and thread them through CLI parsingFASTPQ_METAL_*/FASTPQ_DEBUG_*shims now behave as dev/test fallbacks and are ignored once configuration loads (even when the config leaves them unset); docs/inventory were refreshed to flag the migration.【crates/irohad/src/main.rs:2609】【crates/iroha_core/src/fastpq/lane.rs:109】【crates/fastpq_prover/src/overrides.rs:11】 (IVM_DECODE_TRACE,IVM_DEBUG_WSV,IVM_DEBUG_COMPACT,IVM_DEBUG_INVALID,IVM_DEBUG_REGALLOC,IVM_DEBUG_METAL_ENUM,IVM_DEBUG_METAL_SELFTEST,IVM_FORCE_METAL_ENUM,IVM_FORCE_METAL_SELFTEST_FAIL,IVM_FORCE_CUDA_SELFTEST_FAIL,IVM_DISABLE_METAL,IVM_DISABLE_CUDA) are now gated behind debug/test builds via a shared helper so production binaries ignore them while preserving the knobs for local diagnostics. Env inventory was regenerated to reflect the dev/test-only scope. - FASTPQ fixture updates —
FASTPQ_UPDATE_FIXTURESnow appears only in FASTPQ integration tests; production sources no longer read the env toggle and the inventory reflects the test-only scope. - Inventory refresh + scope detection — The env inventory tooling now tags
build.rsfiles as build scope and tracks#[cfg(test)]/integration harness modules so test-only toggles (e.g.,IROHA_TEST_*,IROHA_RUN_IGNORED) and CUDA build flags show up outside the production count. Inventory regenerated Dec 07, 2025 (518 refs / 144 vars) to keep the env-config guard diff green. - P2P topology env shim release guard —
IROHA_P2P_TOPOLOGY_UPDATE_MSnow triggers a deterministic startup error in release builds (warn-only in debug/test) so production nodes rely solely onnetwork.peer_gossip_period_ms. The env inventory was regenerated to reflect the guard and the updated classifier now scopescfg!-guarded toggles as debug/test.
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 · 91 lines · 0 tokens per session scan A c9ce6010594e
env_var_migration is an agent published in the GitHub repository hyperledger-iroha/iroha (488 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,532 tokens. 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 2026-09-01.
Other agents, from other repositories
agent-request-queue
一次 Agent 运行可能包含多次模型调用、知识库检索、工具执行和文件操作。为了避免同一对话同时修改同一份上下文,Yuxi 把“收到请求”和“开始运行”分成两个阶段,并为每个线程维护 FIFO 队列。.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
review-specialist
Use for isolated code review passes focused on bugs, regressions, contract drift, retrieval integrity, validation gaps, and risky generated-file edits.
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
1-business-analyst
You are an expert business analyst for Aam Digital.
CHANGELOG
All notable changes to the DeFi Agents API are documented in this file.