interpret-flow-ir

A guide for understanding deployed Genesys Cloud Architect flows by reading their intermediate representation, a simplified list of flow steps and connections.

In plain words
What is it for?
Use it to find a flow by name, locate actions containing specific text, trace what connects to what, or inspect how a particular action is configured. It is intended for questions about deployed Genesys Cloud Architect flows.
Why use it?
It prevents the agent from guessing how branches, loops, menus, and jumps work by providing separate methods for discovering content, tracing structure, and inspecting individual actions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/makingchatbots/genesys-cloud-plugins/interpret-flow-ir
Any agent
npx skills add MakingChatbots/genesys-cloud-plugins --skill interpret-flow-ir
Clone the repo
git clone --depth 1 https://github.com/MakingChatbots/genesys-cloud-plugins

Made for: Claude Code, Codex.

Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,043 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00235 $0.05043
Opus 5 $0.00118 $0.02521
Sonnet 5 $0.00047 $0.01009
Haiku 4.5 $0.00023 $0.00504

Measured 2d ago against content hash 745b54c58263, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interpret-flow-ir 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.

skills/interpret-flow-ir/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interpreting Flow IRs

The flow_ir tool returns a deployed flow's intermediate representation (IR): the flow parsed into an explicit control-flow graph, flattened to a node list. Branches, loops, IVR menu choices, and cross-task jumps are already resolved into edges. Answer structural questions from this IR, never by re-deriving control flow from the flow's raw configuration JSON.

The tools are a trio. search_in_flow owns discovery — which actions mention a given name, expression, or phrase (see "Content search"). flow_ir owns structure — what connects to what. flow_action owns semantics — what an individual action is configured to do (see "Action semantics"). The usual order runs the same way: search to find the ids worth caring about, trace to see how they connect, then inspect only those.

All three take a flow id, not a flow name. When only the name is known (e.g. "analyse Book_Payment"), resolve it first with find_flow, which searches flow names and returns each match's id, name, type, and published version.

Tool output shape

On success the tool returns compact JSON: { flowId, ir, warnings }. Failures (flow not found, unparseable configuration, unknown or ambiguous task value) arrive as plain-text tool errors, so any JSON response is a successful parse. warnings is always present; read it before making claims, because each warning scopes what can be asserted (see "Warnings").

ir fields:

Field Meaning
flowName, flowType Flow identity (e.g. inboundcall, digitalbot)
entryTaskId The flow's entry task, when known. Absent when the flow declares no entry or the declared entry is unresolvable (UNRESOLVED_INITIAL_SEQUENCE). Do not fall back to tasks[0], which is then just declaration order
reachabilityIsComplete false when the flow contains intent listen actions whose routing is unmodelled (UNRESOLVED_INTENT_FANOUT). When false, treat every reachable: false as "not provably reachable", never "dead"
tasks Task list { id, name, reusable }. reusable: true marks tasks flagged reusable in Architect
nodes Flat node list, sorted ascending by order

Read the full file on GitHub · 340 lines

Changes

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.

  1. 2d ago First seen · 340 lines · 235 tokens per session scan A 745b54c58263

Subscribe to this mod's changes

interpret-flow-ir is a skill published in the GitHub repository MakingChatbots/genesys-cloud-plugins (9 stars, last pushed 2d ago), licensed MIT. It adds 235 tokens to every session and 5,043 once invoked, about $0.0012 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens