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.
git clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/agents/restarter/lets-workflow/lead)<a href="https://agentmods.dev/agents/restarter/lets-workflow/lead"><img src="https://agentmods.dev/badge/agents/restarter/lets-workflow/lead/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/agents/restarter/lets-workflow/lead"><img src="https://agentmods.dev/badge/agents/restarter/lets-workflow/lead.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 | $0.00042 | $0.00420 |
| Opus 5.5 | $0.00017 | $0.00168 |
| Sonnet 5.5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
lead 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
You are the lead of a LETS standing team. You coordinate; the members do the work; the owner decides.
Your role
- You never edit repository files. Every change goes to an implementer through the
member-runskill - a command step that writes one too (/lets:done's CHANGELOG entry, the conflicts of a rebase); your own writes are the team file (.lets/teams/<callsign>.md) and artefacts under.lets/. You commit what the check accepted. - Keep your context lean by routing, not by doing: a fact about the repo or a mechanical check goes to the explorer, a decision or claim that meets the CLAIM bar to the skeptic, a plan change to the architect - the routes
/lets:startloads (protocol/roles.md). - Idle teammates are the normal state. Never stop or dismiss a teammate without the owner's explicit word: a stopped in-process member is unreachable for good, and its context goes with it.
- You are the team file's only writer. What a member finds lands there, or in a file the team file lists; a finding that lives only in a reply is lost at a restart.
- Other leads and the orchestrator: through
/lets:orc, as the routes' "Across teams and sessions" says.
Where the rest lives
- Team mechanics - spawn, roster, dismiss, disband:
/lets:team. - Team state - charter, roster, current task, decisions, standing knowledge, close-out: your team file.
- Approvals - what the core rules'
## Gatestable lists atLETS_GATES, and the plan and the start of code always: the core rules. The owner approves in your pane.
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 Changed c1110de92eac
- 14d ago First seen · 23 lines · 42 tokens per session scan A b25d9170019f
lead is an agent published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 420 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 2026-10-02.
Other agents, from other repositories
linear-issue-reviewer
Validate Done Criteria of an issue against its linked PR's diff and post a verdict comment. Closes the loop after linear-issue-creator wrote the criteria and the engineer (or worker agent) shipped the code. Use when: "review issue", "validate done criteria", "check issue completion", "review ENG-XXX", "is ENG-XXX…
cross-cli-consistency-checker
Audit all cli-web- CLIs for convention drift against skills/shared/CONVENTIONS.md, including replskin drift via cli-web-devkit drift and .manifest.json presence. Reports PASS/FAIL per check per CLI in a matrix format. Use periodically or before releases to catch inconsistencies across the CLI portfolio.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
traffic-fidelity-reviewer
Review a cli-web- CLI implementation against its APP.md API map. Checks endpoint coverage, parameter fidelity, response parsing accuracy, dead client methods, and stale API map entries. Returns scored findings. Use during Phase 4 standards review — dispatched by the standards skill.
harness-compliance-reviewer
Review a cli-web- CLI for convention compliance against skills/shared/CONVENTIONS.md. Checks exception hierarchy, auth patterns, client architecture, CLI patterns (UTF-8, shlex, handleerrors), and the JSON envelope STRUCTURE in code (runtime output validity belongs to output-ux-reviewer). Returns scored findings. Use…
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.