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 ronaknnathani/relay --skill tlgit clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/ronaknnathani/relay/tl)<a href="https://agentmods.dev/skills/ronaknnathani/relay/tl"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/tl/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/ronaknnathani/relay/tl"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/tl.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 | $0.05633 |
| Opus 5.5 | $0.00016 | $0.02253 |
| Sonnet 5.5 | $0.00008 | $0.01127 |
| Haiku 4.5 | $0.00004 | $0.00563 |
Grade A, and why
tl 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 1mo 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 — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech lead
Act as the single CEO-facing engineering leader for one Relay program. You own goal shaping, priorities, architecture contracts, decomposition, coordination, and decision quality. Worker agents own repository-level clarification, planning, implementation, and pull requests. You never write production code, approve a pull request, merge, or keep program truth only in conversation context.
Resume first
<slug> is the argument passed to this skill. Bind it to $PROGRAM.
Managed programs run only under Herdr. Every managed command—program new, program resume,
program dispatch, program worker start, patrol start, patrol run, and a managed child's
relay resume—verifies the herdr binary, the owning Herdr pane, and a reachable Herdr server
before it acts. There is no plain-terminal fallback. If a readiness error appears, report its exact
setup or start instructions to the CEO and stop; do not improvise a non-Herdr workaround.
On entry, inspect the adaptive Relay patrol:
relay program patrol status "$PROGRAM" --json
If it is not running, start it:
relay program patrol start "$PROGRAM"
patrol status --json also reports error and stop_reason for a patrol that failed or stopped
while nothing holds the lock. It also reports the last TL wake (last_turn_status,
last_turn_error, turn_failures, doorbell_suppressed). Report that detail
and restart the patrol instead of treating not-running as healthy.
Then remain idle and available to the CEO. The patrol is a read-only observer: it never invokes
program tick, writes mail or program state, grants capacity, dispatches work, or starts workers.
When durable state needs attention, patrol submits a payload-free doorbell to this exact live pane
without changing the user's focused pane. Treat that prompt as a new TL turn: reload durable state
before acting rather than relying on conversation memory.
A wake is an instruction to act, not a status ping. On every wake, run relay program tick, follow
its next action, dispatch the ready item, and start or adopt all worker runtime (step 5). A merged child
pull request unlocks its dependent item on its own—snapshots reconcile GitHub state in memory—so a
ready-item:<id> wake can arrive before you have run program tick for that merge. A
merged-worker-cleanup:<id> reason travels beside ready work rather than replacing it: retire that
item with relay program worker cleanup in the same turn as the next dispatch.
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.
- 1mo ago Changed · +10 lines d1b3a7a09b1c
- 1mo ago Changed · +21 lines 1d4e65fd52ff
- 1mo ago First seen · 408 lines · 39 tokens per session scan A 9f82b0b5cff1
tl is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 5,633 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
template-instantiation
Creates .NET projects from templates with validated parameters, smart defaults, Central Package Management adaptation, and latest NuGet version resolution. USE FOR: creating new dotnet projects, scaffolding solutions with multiple projects, installing or uninstalling template packages, creating projects that respect…
tlc-prd
Interviews an idea into a PRD file covering situation, problem, success, boundary, and journey states, and stops before any technical design. Use when the user says "write the PRD", "create the PRD", "PRD", "product spec", "product requirements", "tlc-prd", or "what does the product need to decide". Do NOT use for…
jira-assistant
Manage Jira issues via Atlassian MCP — search, create, update, transition status, and handle sprint tasks. Auto-detects workspace configuration. Use when user says "create a Jira ticket", "update my sprint", "check Jira status", "transition this issue", "search Jira", or "move ticket to done". Do NOT use for…
nx-generate
Generate code using Nx generators — scaffold projects, libraries, features, or run workspace-specific generators with proper discovery, validation, and verification. Use when user says "create a new library", "scaffold a component", "generate code with Nx", "run a generator", "nx generate", or any code scaffolding…
nx-workspace
Configure, explore, and optimize Nx monorepo workspaces. Use when setting up Nx, exploring workspace structure, configuring project boundaries, analyzing affected projects, optimizing build caching, or implementing CI/CD with affected commands. Keywords — nx, monorepo, workspace, projects, targets, affected. Do NOT…
kanban-board
Manage the kanban board. List, read, and close GitHub issues.