oc-signal-forge

oc-signal-forge is a skill for Claude Code from asfbay-bit/opchain-skills. It costs 184 tokens per session (4,638 once invoked), scanned A, original, Apache-2.0.

An analytics backend workflow for turning a question into a measurable signal. It designs the metric, collects and transforms the data, stores it, and checks that the result answers the intended question.

In plain words
What is it for?
Use it to define new metrics, design instrumentation, build data collection and transformation pipelines, and verify signals before connecting them to dashboards or other consumers.
Why use it?
It helps prevent dashboards from showing accurate numbers that measure the wrong thing. Separate design, implementation, and skeptical evaluation expose mistakes before the signal is used.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the opchain plugin — 33 skills, 12 commands, 3 hooks shipped together

Good fit Use it to define new metrics, design instrumentation, build data collection and transformation pipelines, and verify signals before connecting them to dashboards or other consumers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asfbay-bit/opchain-skills/oc-signal-forge
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.

Any agent
npx skills add asfbay-bit/opchain-skills --skill oc-signal-forge
Clone the repo
git clone --depth 1 https://github.com/asfbay-bit/opchain-skills

Made for: Claude Code.

Or install opchain, the plugin that ships this one along with the rest of its 33 skills, 12 commands, 3 hooks.

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 oc-signal-forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-signal-forge/github.svg)](https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-signal-forge)
Your own site
<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-signal-forge"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-signal-forge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for oc-signal-forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-signal-forge"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-signal-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00184 $0.04638
Opus 5 $0.00092 $0.02319
Sonnet 5 $0.00037 $0.00928
Haiku 4.5 $0.00018 $0.00464

Measured 7d ago against content hash 62a619bd16f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

oc-signal-forge 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 7d 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.

plugins/opchain/skills/oc-signal-forge/SKILL.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signal Forge

On first invocation, read references/orchestrator.md and follow its welcome protocol.

Owns the backend of analytics: instrumentation design, the harvester / ingestion layer, the transform / middleware, the store, and — the part most analytics tooling skips — validation that the signal answers the question correctly, before it's ever exposed. The dashboarding front end already exists (oc-dash-forge); this is the skill that feeds it a number you can trust.

The hard part of analytics is not laying pipe. It's proving the number is right. A pipeline that runs is not a pipeline that's correct, and a metric that's correct can still answer the wrong question — "active users" computed from raw page-loads is a perfectly accurate count of the wrong thing. Signal Forge exists because that silent failure mode is the default outcome of every dashboard built without an adversarial check between the data and the chart.

So this is a -forge tri-agent harness. A Designer defines the metric and its instrumentation spec from the question it serves, a Builder implements the instrumentation + harvester + transform + store, and an Evaluator is skeptical about correctness — it tries to disprove the number against an independent ground truth and tests whether the signal actually answers the framed question. Only a signal that survives the Evaluator gets wired to a consumer. Signal Forge does not render charts, meter the opchain pipeline's own usage, or watch prod uptime — see Boundaries.


/oc-signal — Command Reference

SIGNAL FORGE COMMANDS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

  FRAME (Phase 0 — the anchor)
  /oc-signal frame      State the decision the metric informs + the question it answers

  DESIGNER (Phase 1)
  /oc-signal design     Produce the signal spec: definition, grain, instrumentation schema

  BUILDER (Phase 2)
  /oc-signal harvest    Select + scaffold the harvester archetype for this source
  /oc-signal build      Implement instrument + harvest + transform + store + consumer stub

  EVALUATOR (Phase 3 — the signature gate)
  /oc-signal verify     Adversarial pass: answers-the-question, correctness, robustness, wired

  WIRE (Phase 4)
  /oc-signal wire       Hand the validated signal to its consumer (oc-dash-forge / oc-api-dev)

  REGISTRY & STATE
  /oc-signal catalog    Show / update the living signal catalog (signals/catalog.md)
  /oc-signal status     Show checkpoint status — which signal, which phase, what's next
  /oc-signal            Show this command reference

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Type any command to begin. /oc-signal to see this again.

Read the full file on GitHub · 375 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago Changed · +10 lines · +45 tokens per session 62a619bd16f2
  2. 10d ago First seen · 365 lines · 139 tokens per session scan A c137aace24ca

Subscribe to this mod's changes

oc-signal-forge is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 184 tokens to every session and 4,638 once invoked, about $0.0009 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens