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 agentmods add skills/mohammad19974/bounded-relay/setupnpx skills add mohammad19974/bounded-relay --skill setupgit clone --depth 1 https://github.com/mohammad19974/bounded-relayWhat 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 | $0.00027 | $0.00345 |
| Opus 5 | $0.00014 | $0.00172 |
| Sonnet 5 | $0.00005 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
boundedrelay-setup 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 yesterday.
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
Set up BoundedRelay
Use this skill when the user wants to connect or diagnose BoundedRelay.
- Confirm Node.js satisfies the version declared by the installed BoundedRelay
package and that
boundedrelayresolves onPATH. - Run
boundedrelay doctor. Report the observed Codex CLI, authentication, allowed roots, model allowlist, proposal state, limits, and blockers. Never print tokens or inherited environment. - Confirm the MCP server exposes
codex_worker_capabilities,codex_worker_workspace,codex_worker_sdd_route, andcodex_worker_sdd_review. Proposal support is optional and must be explicitly enabled by the user. - Resolve the intended consumer repository through
codex_worker_workspace. Never widen allowed roots merely to make a check pass. - Keep Claude Code's current host model. This plugin intentionally has no model override. Report a Claude model label only when the host supplies trustworthy metadata; otherwise say unavailable.
- For Spec Kit, direct the user to the adjacent
integrations/spec-kit/README.md. Do not initialize Spec Kit, install an extension, edit.gitignore, or create commits without matching authority.
BoundedRelay is a one-way local boundary: Claude coordinates and may call Codex. Codex cannot call Claude through this plugin. Jobs are process-memory state and disappear when the MCP server exits.
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.
- yesterday First seen · 34 lines · 27 tokens per session scan A 0013de0fcfd1
boundedrelay-setup is a skill published in the GitHub repository mohammad19974/bounded-relay (1 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 345 once invoked, about $0.0001 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
thesis-control
Use when AI-assisted thesis edits risk claim drift, scope creep, loss of author control, or repeated revisions that fail to converge; provides spine cards, edit contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe academic manuscript drafts that read like engineering reports, module inventories, internal validation packets, or system notes into paper-form scientific arguments with clear gap, contribution chain, results narrative, figure/table roles, AI-assisted component boundaries, and submission-readiness blockers.
argument-governance
Build and audit the manuscript argument system: intent, gap-contribution alignment, hierarchical claims, evidence balance, limitations, and reviewer attack surfaces. Use when a paper, thesis chapter, review article, or rebuttal needs explicit intent registers, contribution chains, claim hierarchy, argument maps…
evidence-review
Build evidence-controlled literature reviews and gap maps with source-status labels, claim registers, citation-role plans, traceability tables, and overclaim audits. Use when drafting or auditing review papers, thesis literature reviews, scoping reviews, or evidence syntheses where adjacent-domain evidence, candidate…
peer-review
Review another author's manuscript, paper, thesis chapter, proposal, or preprint as an external reviewer. Use when asked to evaluate novelty, significance, gap-contribution fit, claim-evidence adequacy, methods, evaluation, overclaim risks, structure, writing, required revisions, or recommendation without rewriting…
codex-memory-trim
Manage Codex's native global memory (/.codex/memories) with three sub-procedures - trim (audit + dedupe + three-layer cleanup), compress (rewrite verbose memories into concise form), and add-global (add a custom global rule/preference). Use when the user asks to 精简/清理/整理/压缩 Codex 记忆, 去重, 简化冗长记忆, 添加/写入/修改全局记忆 or a…