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/restarter/lets-workflow/backlog-workflownpx skills add restarter/lets-workflow --skill backlog-workflowgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.00051 | $0.01100 |
| Opus 5 | $0.00026 | $0.00550 |
| Sonnet 5 | $0.00010 | $0.00220 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
backlog-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog-workflow (Dynamic Workflow asset)
A Dynamic Workflow asset (see CLAUDE.md -> "Dynamic Workflow Assets"; review-workflow is the reference example). backlog.workflow.js is executed by the Workflow tool, invoked from /lets:backlog's Workflow Mode via:
Workflow({ scriptPath: "${CLAUDE_PLUGIN_ROOT}/skills/backlog-workflow/backlog.workflow.js", args })
${CLAUDE_PLUGIN_ROOT} is substituted at command-load time, so backlog.md carries the literal absolute path. Treat backlog.workflow.js as a template the command points at, not a script to reproduce inline.
Why this is a transparent performance lever (not autonomous)
/lets:backlog review --workflow produces the SAME result as the standard Task path - only the per-agent backlog-idea dumps stay off-context. The explorer scout (Phase 1) and the signal-driven agent selection (Phase 2) stay IN-CONTEXT in backlog.md; the ideate fan-out (Phase 3) and the aggregate/cluster (Phase 4) move into the workflow (off-context). The interactive dialog (Phase 5) + capture (Phase 6) stay in-context after the aggregate returns. There is no Web Research stage: the standard backlog Phase 3 ideates over the project's own profile + CLAUDE.md without web search, so adding web here would diverge the two paths - --workflow must stay a pure context-savings lever, same findings. The cluster is a SEMANTIC dedupe + impact-sort (an off-context merge), not a quality gate.
What it does (off-context)
- Ideate - fan out the selected
lets:<name>agents in parallel over the explorer's Project State Profile + CLAUDE.md (structuredIDEA_SCHEMA: title, category=missing|adjust|theme, impact, description).adjustideas embed the referenced task as Title (task-id) in description. - Cluster (off-context agent + deterministic attribution) - a neutral subagent (no
agentType) groups raw ideas into themes, merging ideas that make the same point even when worded differently (CLUSTER_SCHEMA: themes carrying member indices).buildThemescomputes each theme'sagents[]+ impact deterministically (high if any member is high) and guarantees no idea is dropped. Falls back to title-only dedup (clusterIdeas) if the cluster agent errors or returns nothing; skips the agent for <=1 idea.
What ships with it
1 file 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.
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.
- 2d ago First seen · 46 lines · 51 tokens per session scan A aa2ff3cc39cc
backlog-workflow is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 1,100 once invoked, about $0.0003 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.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.