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 commands/restarter/lets-workflow/donegit 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 | $0.00012 | $0.08777 |
| Opus 5 | $0.00006 | $0.04389 |
| Sonnet 5 | $0.00002 | $0.01755 |
| Haiku 4.5 | $0.00001 | $0.00878 |
Grade A, and why
done scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 769 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Done
Complete the current task. Document work, create PR or merge locally, close in the tracker.
This is NOT session end. Use /lets:end to end a session. /lets:done finishes a TASK.
Convention used in this file (per CLAUDE.md "Naming Convention: LETS_*"):
{LETS_FOO}placeholder inside```bashsnippets AND AskUserQuestion strings - the orchestrator substitutes the literal value before running / before the tool call. Required because Bash tool calls are fresh shells ($LETS_FOOunset) and AskUserQuestion renders strings literally.$LETS_FOOin prose and section headings only - read-only reference to the LETS Config inject. Do NOT use$LETS_FOOin bash blocks or AskUserQuestion strings - it silently produces wrong commands or a literal$LETS_FOOin the rendered question.
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.
Step 1: Active Task Detection
Use the detect-task skill to find the active task: Skill(skill: "lets:detect-task").
If no task found: ask user which task to close.
Epic Guard
Check the detected task's type via the tracker's show verb (beads exposes type; an adapter that doesn't expose a type can't epic-guard - skip it).
If type is epic - do NOT close it automatically:
- Inform user: "This is an epic. Epics stay open for future tasks."
- Offer: close a specific child task instead, or confirm epic closure if user insists.
Trunk-mode Routing
Several steps below have a conditional branch for trunk-mode — when HEAD is $LETS_MERGE_BRANCH (user opted in via the take-task picker option "Stay on current branch"). The check is HEAD-based at runtime via git branch --show-current compared to $LETS_MERGE_BRANCH from LETS Config; no persistent flag.
In trunk-mode the following gates fire:
- Step 4 commit range:
start:..HEAD(the task boundary from.task-<slug>, not$LETS_MERGE_BRANCH..HEAD, which is empty when HEAD IS the merge-branch) - Already-Merged Guard: skip (PR on same-source-target is not a valid PR, nothing to detect)
- Step 6 confirm: trunk-mode wording (push + close, no PR)
- Step 7 completion comment: commit range uses
start:..HEAD(same reason as Step 4) - Step 8 finish: upstream-aware push + close (tracker
closeverb; no PR, no merge, nogit branch -d) - Step 9 output: trunk-mode "Next" options (no "Merge & close", no "Switch to merge-branch")
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 · 769 lines · 12 tokens per session scan A 5a14b7ac8115
done is a command published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 12 tokens to every session and 8,777 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.