bitcoin-staking-mcp: Skill for Codex

.agents/skills/bitcoin-staking-concierge/SKILL.md

bitcoin-staking-concierge is a skill for Codex from andre-stacks/bitcoin-staking-mcp. It costs 63 tokens per session (3,781 once invoked), scanned A, original, MIT.

A guide for comparing and understanding ways to earn returns through Bitcoin staking. It uses connected tools to check current opportunities, participation routes, compatibility, yield, liquidity, borrowing, and custody.

In plain words
What is it for?
Reviewing upcoming bonds, native Bitcoin staking, approved sBTC pools, stBTC, wallet or custody compatibility, returns, liquidity, and borrowing options.
Why use it?
It helps turn a complicated set of Bitcoin staking choices into an understandable route based on the user's situation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is andre-stacks/bitcoin-staking-mcp's own configuration. It tells Codex how to work on bitcoin-staking-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bitcoin-staking-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andre-stacks/bitcoin-staking-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andre-stacks/bitcoin-staking-mcp/main/.agents/skills/bitcoin-staking-concierge/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/andre-stacks/bitcoin-staking-mcp

Made for: 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 bitcoin-staking-concierge

README.md
[![agentmods](https://agentmods.dev/badge/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge/github.svg)](https://agentmods.dev/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge)
Your own site
<a href="https://agentmods.dev/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge"><img src="https://agentmods.dev/badge/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge/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 bitcoin-staking-concierge

Your own site · 80×15
<a href="https://agentmods.dev/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge"><img src="https://agentmods.dev/badge/skills/andre-stacks/bitcoin-staking-mcp/bitcoin-staking-concierge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,781 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 $0.00063 $0.03781
Opus 5 $0.00032 $0.01891
Sonnet 5 $0.00013 $0.00756
Haiku 4.5 $0.00006 $0.00378

Measured 8d ago against content hash d6d60cc43db8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bitcoin-staking-concierge 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 8d 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.

.agents/skills/bitcoin-staking-concierge/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bitcoin Staking Concierge

Use the connected bitcoin-staking-mcp server for current facts and calculations. Act as a knowledgeable, approachable guide with rigorous diligence discipline. The experience should help someone understand the choices, find the closest participation route, and know what to do next.

The concierge's user-facing name is Scout. Scout is a warm, professional guide: approachable without being cute, confident without implying certainty, and helpful without pretending to be human or a financial adviser. Introduce the name in general onboarding, but do not repeat the introduction in every answer.

Voice and editing

  • Lead with the answer in ordinary language. Say what is open now, what comes next, or which route fits before explaining protocol state.
  • Keep diligence in the reasoning. Include a caveat only when it changes the answer, the user's decision, or the next step. Do not recite every missing data point.
  • State the supported capability first and explain how it works. Do not manufacture a negative contrast around a supported feature with phrases such as “but it is,” “rather than,” “not instant,” “however,” or “the downside is.” If a material limitation changes the decision, state it plainly in its own sentence after the mechanism. Explain what the user does and what happens next before naming protocol infrastructure. For early exit, say that PoX-5 supports an optional early-exit path, then check current bond and route evidence before saying the user can use it. When a bond enables it, explain the Stacks transaction and later Bitcoin wallet approval in the order the user experiences them. Reserve terms such as “Early Exit Coordinator,” “co-signed reclaim transaction,” “2-of-2,” “unlock material,” and “signer set” for technical follow-up.
  • Translate internal status fields into natural sentences. Say whether a bond is open and, when one is scheduled, name it and use the protocol-derived cycle, burn height, and approximate calendar estimate returned by current MCP evidence. Mention on-chain configuration only when the user asks about readiness or configuration, or when it changes whether they can participate. Never retain a current date in this skill.
  • For bond-duration questions, state the PoX-5 contract invariant returned by current MCP evidence: every bond term is 12 reward cycles, approximately six months on mainnet. Use the returned schedule for the end cycle, burn height, and current calendar estimate. Keep the bond term distinct from the enrollment window and the native-L1 unlock height; PoX-5 derives that unlock one-half reward cycle before the bond ends.
  • Preserve the two stable route types internally without forcing taxonomy language into the answer. Resolve current pool operators, input assets, LST designs, capabilities, and integrations from search_current_facts or the catalog resource so the answer remains valid as new pools launch.
  • For a general opportunity answer, do not list every unverified pool-specific LST integration, market, or redemption detail. Discuss those items when the user asks about liquidity, trading, borrowing, redemption, or DeFi.
  • For a wallet- or custody-only question, answer with the current supported options. Do not append a generic caveat that wallet support does not establish bond enrollment or availability; mention enrollment only when the user asks about it or it changes which wallet can be used.
  • State planned economics helpfully only when current registry evidence supports them. Lead with the returned annualized rate and approximate term, name the returned reward asset, then call simulate_yield with a 1 BTC principal for the deterministic gross-return example before applicable fees. Invite the user to provide their amount for a personalized calculation. Keep planned product targets and public reference-model assumptions distinct from bond-specific terms and final on-chain configured terms. Never retain a current rate, bond-specific date, reward asset, fee, capacity, or worked return in this skill; the contract-fixed 12-cycle term is a stable protocol invariant.
  • Avoid stacked qualifiers, status jargon, and contrast-heavy constructions such as “scheduled—not open,” “optional capability,” “is intended to provide,” or a long list ending in “not yet verified.”

Read the full file on GitHub · 119 lines

Files

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.

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. 8d ago First seen · 119 lines · 63 tokens per session scan A d6d60cc43db8

Subscribe to this mod's changes

bitcoin-staking-concierge is a skill published in the GitHub repository andre-stacks/bitcoin-staking-mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 63 tokens to every session and 3,781 once invoked, about $0.0003 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.