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 equinoxaifinance-rgb/living-stack-mcp --skill living-stackgit clone --depth 1 https://github.com/equinoxaifinance-rgb/living-stack-mcpWrote 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/equinoxaifinance-rgb/living-stack-mcp/living-stack)<a href="https://agentmods.dev/skills/equinoxaifinance-rgb/living-stack-mcp/living-stack"><img src="https://agentmods.dev/badge/skills/equinoxaifinance-rgb/living-stack-mcp/living-stack/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/equinoxaifinance-rgb/living-stack-mcp/living-stack"><img src="https://agentmods.dev/badge/skills/equinoxaifinance-rgb/living-stack-mcp/living-stack.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 | $0.00030 | $0.00253 |
| Opus 5.5 | $0.00012 | $0.00101 |
| Sonnet 5.5 | $0.00006 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
living-stack 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 2mo 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.
What it actually says
Living Stack MCP
Use the server as a control-and-proof plane. The host remains the executor.
- Call
livingstack.statusbefore a consequential workflow. - Start one scoped session with an explicit goal and budget.
- Put only relevant, provenance-labeled context into that session.
- Authorize an action before executing it in the host.
- Record the actual classification, cost, typed evidence, and safe evidence
references after execution, then retain the returned
outcome_id. - Use
livingstack.check_claimbefore making completion, integrity, working, or deployment claims. Pass the exact authorization target again assubjectand select only the explicit supportingoutcome_ids; never pool evidence from unrelated outcomes in the session. - Save a checkpoint before risky transitions and verify it when resuming.
- Close the session and export a signed trace when the workflow is terminal.
Never treat an authorization receipt as proof the host action occurred. Never treat a workspace signature as proof of publisher identity.
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.
- 2mo ago First seen · 25 lines · 30 tokens per session scan A 8f1d684b01f3
living-stack is a skill published in the GitHub repository equinoxaifinance-rgb/living-stack-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 253 once invoked, about $0.0001 per session on Opus 5.5. 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
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.
openworkproof-soc-review
Review supplied Slips alerts with OpenWorkProof's reference SOC workflow and verify its signed evidence bundle. Use for alert investigation and evidence review; connecting MCP alone does not activate endpoint protection.
atrib
Use atrib as the verifiable substrate for memory, reasoning, and getting sharper over time, not as instrumentation that observes you from the outside. atrib gives the agent two cognitive verbs: attest (write: sign an observation, mark a past record's importance, or supersede a prior position) and recall (read: look up…
trustcard-operations
Set up and operate Trustcard gates for MCP coding tools, explain tool denials, check manifest drift and expiry, renew unchanged contracts, and inspect local tool access. Use for Trustcard or MCP tool governance requests.
causallayer-mcp
This skill provides instructions for AI agents interacting with the CausalLayer Model Context Protocol (MCP) server. CausalLayer is a deterministic AI liability apportionment engine. It takes an incident report and mathematically proves which agent, vendor, or operator is liable based on counterfactual do-calculus…
motion-design-replication
Rebuild the feel of a reference motion-design clip (camera, depth of field, easing, captions, outro) as an on-brand agent-swarm piece in Remotion, then prove it with side-by-side frames and a model re-read of the replica. Use when asked to "replicate this video's vibe for the swarm", "make one like this but ours", or…