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 skills add asfbay-bit/opchain-skills --skill oc-signal-forgegit clone --depth 1 https://github.com/asfbay-bit/opchain-skillsWrote 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/skills/asfbay-bit/opchain-skills/oc-signal-forge)<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.
<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>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 5.1 | $0.00184 | $0.04638 |
| Opus 5 | $0.00092 | $0.02319 |
| Sonnet 5 | $0.00037 | $0.00928 |
| Haiku 4.5 | $0.00018 | $0.00464 |
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.
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.
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.
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.
- 7d ago Changed · +10 lines · +45 tokens per session 62a619bd16f2
- 10d ago First seen · 365 lines · 139 tokens per session scan A c137aace24ca
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…