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 Nolane-x/forge-os --skill controlling-ai-costgit clone --depth 1 https://github.com/Nolane-x/forge-osWrote 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/nolane-x/forge-os/controlling-ai-cost)<a href="https://agentmods.dev/skills/nolane-x/forge-os/controlling-ai-cost"><img src="https://agentmods.dev/badge/skills/nolane-x/forge-os/controlling-ai-cost/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/nolane-x/forge-os/controlling-ai-cost"><img src="https://agentmods.dev/badge/skills/nolane-x/forge-os/controlling-ai-cost.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 | $0.00039 | $0.01539 |
| Opus 5 | $0.00019 | $0.00770 |
| Sonnet 5 | $0.00008 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
controlling-ai-cost 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Controlling Ai Cost
Overview
This skill owns one bounded responsibility: controlling ai cost. Its focus is controlling ai cost within ai-products product boundaries. It converts declared inputs into typed artifacts and reproducible evidence without silently changing product scope.
Trigger
Activate only when the project is in one of these stages: product-definition, ux-design, architecture, planning, implementation, verification, release-readiness, all contract preconditions pass, and the router identifies a missing output this skill can produce. Do not activate merely because the skill name resembles the user request.
Required Inputs
product-definition- Optional:
architecture-decision - Optional:
verified-build - Current gate result, open findings, artifact hashes, and invalidation state
- Required tools: none
- Optional tools: none
- Confirmed human decisions relevant to this scope
Method-Specific Protocol
- Define the exact decision, actors, objects, states, invariants, side effects, and non-goals owned by controlling ai cost.
- Build a decision table for normal, boundary, invalid, permission, failure, retry, recovery, concurrency, migration, and abuse conditions relevant to controlling ai cost.
- Apply controlling ai cost only to direct input artifacts; record assumptions, rejected alternatives, and any human decision still required.
- Trace the resulting contract to user value, security, reliability, cost, operability, and downstream consumers.
- Create reproducible checks that would fail if controlling ai cost were incomplete or implemented incorrectly.
Procedure
- Read the confirmed product definition, domain context, assurance profile, and active findings.
- Identify the domain objects, actors, state transitions, regulations, provider boundaries, and operational constraints owned by this skill.
- Define the exact decision, actors, objects, states, invariants, side effects, and non-goals owned by controlling ai cost.
- Build a decision table for normal, boundary, invalid, permission, failure, retry, recovery, concurrency, migration, and abuse conditions relevant to controlling ai cost.
- Apply controlling ai cost only to direct input artifacts; record assumptions, rejected alternatives, and any human decision still required.
- Trace the resulting contract to user value, security, reliability, cost, operability, and downstream consumers.
- Create reproducible checks that would fail if controlling ai cost were incomplete or implemented incorrectly.
- Model normal, boundary, failure, recovery, permission, concurrency, migration, and abuse behavior before implementation.
- Define stable contracts and explicit non-goals; do not leak domain concerns into unrelated modules.
- Create executable acceptance, negative, resilience, and compatibility checks proportional to risk.
- Publish the domain artifact, evidence packet, unresolved assumptions, and downstream invalidations.
What ships with it
1 file 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 First seen · 136 lines · 39 tokens per session scan A 9b22b50a151d
controlling-ai-cost is a skill published in the GitHub repository Nolane-x/forge-os (10 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,539 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
claw-metagenomics
Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways.
clawrouter
Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.
company-analyzer
A company-analysis tool that calls language models to produce analyses such as SWOT, valuation, and industry reviews. It includes shell helpers for caching results, tracking API costs, and checking a daily budget.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
memory-optimization
Tune moflo's memory stack for speed, RAM, and index quality. Covers HNSW parameters (M, efConstruction, ef), vector quantization, batch operations, and common bottlenecks. Use when scaling past 100k entries or when search latency regresses.
memory-patterns
Persistent memory patterns for moflo agents — session memory, long-term knowledge, pattern learning, and cross-session context via moflo's node:sqlite + HNSW vector store. Use when building stateful agents or assistants that need to remember across runs.