agentmods.dev

sshx

A lightweight review workflow that asks separate workers to examine a risky decision or implementation from different perspectives and reach a consensus. It is designed for one decision or task, not a long-running process.

In plain words
What is it for?
Use it for high-risk choices, multi-angle reviews, consensus building, and a final same-shape review of a completed change.
Why use it?
It helps expose problems in architecture, correctness, safety, cost, or product decisions before implementation or final sign-off.

Skill for Claude CodeCodex

24 5d ago A scan 43 tokens original MIT
View the source file ChronoAIProject/consensus-rnd
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.

agentmods
npx agentmods add skills/chronoaiproject/consensus-rnd/sshx
Any agent
npx skills add ChronoAIProject/consensus-rnd --skill sshx
Clone the repo
git clone --depth 1 https://github.com/ChronoAIProject/consensus-rnd

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,613 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.14613
Opus 5 $0.00022 $0.07306
Sonnet 5 $0.00009 $0.02923
Haiku 4.5 $0.00004 $0.01461

Measured 2d ago against content hash 8d9a7157c424, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sshx 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 2d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/clean-codex-worker-runs.sh, scripts/read-codex-worker-status.sh, scripts/run-codex-worker-batch.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sshx/SKILL.md · 630 lines

How it starts

The opening of the file, as written. The whole thing — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sshx

sshx is a lightweight worker-delegated inline consensus skill. It applies the consensus engine philosophy to a single decision or implementation task by dispatching isolated worker perspectives without depending on any long-running runtime or lifecycle surface.

Trigger

Use this skill when:

  • a decision has meaningful product, architecture, correctness, safety, or cost risk;
  • the user asks for multi-angle thinking, consensus, or review without starting a long-running work-unit loop;
  • a concrete plan should be tested against independent perspectives before implementation;
  • a finished change should pass a same-shape review gate before declaring done.

Do not use this skill for routine one-step answers where no separate perspectives would change the outcome, and do not run it when the decision's stakes cannot justify the protocol's cost: whether to run it follows decision risk, not available budget.

Goal Contract

GoalArtifact is a prompt-level record, not a runtime API. It is written during intake before worker mode selection or any worker dispatch.

GoalArtifact has exactly these fields:

  • raw_user_input
  • normalized_goal
  • constraints
  • success_criteria
  • iteration_question
  • harness
  • revisions

harness is a prompt-level record containing exactly these three sub-items:

  • provided_capabilities: capabilities already supplied by the execution environment that the skill must not implement again;
  • trust_boundary: which roles are trusted and which are untrusted. The trusted declaration is non-adversarial, not infallible: failures, omissions, and uncertainty by a trusted party remain fully in review scope;
  • decision_ownership: product, governance, and boundary decisions; engineering judgments; and orchestration judgments, each assigned to its owner.

revisions is an append-only list whose each item contains exactly these three sub-items:

  • change: what was corrected;
  • authorization_source: where authorization came from;
  • invalidated_completed_work: completed work invalidated by the correction, or none.

Read the full file on GitHub · 630 lines

Files

What ships with it

8 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. 2d ago First seen · 630 lines · 43 tokens per session scan A 8d9a7157c424

Subscribe to this mod's changes

sshx is a skill published in the GitHub repository ChronoAIProject/consensus-rnd (24 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 14,613 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 2026-08-30.

Code reviewPlanning
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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens