declare-parameter-producers

declare-parameter-producers is a skill for Claude Code, Codex from radiantlogicinc/fastworkflow. It costs 120 tokens per session (1,372 once invoked), scanned A, original, Apache-2.0.

A declaration that says which commands can produce a parameter needed by another command. It turns relationships between commands into a sequence the planner can follow.

In plain words
What is it for?
Use it when one command needs an identifier or handle returned by another command, and when missing-parameter messages should point callers to the right producer.
Why use it?
It prevents the planner from having to guess how to obtain missing IDs, handles, codes, or other values.

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/radiantlogicinc/fastworkflow/declare-parameter-producers
Any agent
npx skills add radiantlogicinc/fastworkflow --skill declare-parameter-producers
Clone the repo
git clone --depth 1 https://github.com/radiantlogicinc/fastworkflow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for declare-parameter-producers

README.md
[![agentmods](https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/declare-parameter-producers.svg)](https://agentmods.dev/skills/radiantlogicinc/fastworkflow/declare-parameter-producers)
Your own site
<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/declare-parameter-producers"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/declare-parameter-producers.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,372 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 $0.00120 $0.01372
Opus 5 $0.00060 $0.00686
Sonnet 5 $0.00024 $0.00274
Haiku 4.5 $0.00012 $0.00137

Measured 5d ago against content hash 19fd2dd44156, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

declare-parameter-producers 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 5d 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.

fastworkflow/skills_for_coding_fastworkflows/declare-parameter-producers/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Declaring parameter producers with available_from

A command that takes an opaque handle — an id, uid, code, ticket number — cannot be called until something produces that handle. available_from records which command that is, turning a flat list of commands into a graph the planner can walk.

The hint

On the Input field, context-qualified:

class Signature:
    class Input(BaseModel):
        order_id: str = Field(
            description="The order to fetch",
            examples=["#W0000000"],
            json_schema_extra={'available_from': ['CustomerDesk/find_order']},
        )

The value is a list — name every command that can legitimately supply the handle.

Who reads it

Two consumers, and they behave differently:

  1. The planner. Its instruction is literally to walk the graph of available_from hints to build the command sequence. The hints are the only structured statement of "you must call X before Y", so an unhinted handle parameter is a parameter the planner has to guess its way to.
  2. The missing-parameter message. When validation finds the field absent, it appends use the <producers> command(s) to get <field> information. A human caller is told to abort and use ...; an agent (run_as_agent set on the workflow context) is told to just use it, because the agent can chain without abandoning the turn.

Only Input fields are read. Putting the hint on an Output field does nothing.

The hint is surfaced only when the field is missing, so it never substitutes for description — write both.

Rule 1 — name a producer the caller can actually reach

A hint naming a command the caller cannot invoke is worse than no hint: it sends the planner down a path that dead-ends. Reachable means either

  • on the calling context's own surface, own or inherited, or
  • on a live ancestor's surface, since a wildcard prediction escalates up the runtime parent chain and serves the command there without a navigation turn.

Read the full file on GitHub · 138 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. 5d ago First seen · 138 lines · 120 tokens per session scan A 19fd2dd44156

Subscribe to this mod's changes

declare-parameter-producers is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 1,372 once invoked, about $0.0006 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.

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