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/artifact-pathnpx skills add restarter/lets-workflow --skill artifact-pathgit 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 | $0.00053 | $0.00871 |
| Opus 5 | $0.00026 | $0.00436 |
| Sonnet 5 | $0.00011 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
artifact-path 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact Path
.lets/ is ONE directory shared by every worktree of the repo (whole-dir symlink). Two sessions writing the same artifact kind on the same day used to overwrite each other (lets-05c4s - a plan review was lost). This skill is the single place that names an artifact and guarantees the path is free.
Contract: args kind=<kind> ext=<md|json> [task=<task-id>]. Output: ONE echoed line ARTIFACT_FILE=<absolute path>. The caller writes to that path VERBATIM - never recomputes the stamp, never strips the -vN suffix, never writes anywhere else.
Name shape
{YYYY-MM-DD}-{HHMM}-{ID}-{KIND}[-vN].{EXT} under the kind's directory:
| kind | directory |
|---|---|
plan |
.lets/plans/ |
review-local, review-branch, review-pr-<n>, review-plan |
.lets/reviews/ |
snapshot, snapshot-precompact |
.lets/sessions/ |
ID is the task id when one is active (MANDATORY whenever a task exists - same rule as feature/<task-id>-... branches). With no task: {branch-slug}-{6hex}, 6hex = first 6 chars of $CLAUDE_CODE_SESSION_ID, so two taskless sessions on main still get distinct names. -vN (v2, v3, ...) is appended whenever the path already exists - for task and taskless alike.
Step 1: Resolve the task id
If the caller passed task=, use it. Otherwise invoke Skill(skill: "lets:detect-task", args: "fallback=no") and use its result (may be empty). fallback=no is mandatory: the searched fallback asks a question, and a taskless snapshot on /lets:end must stay silent.
Step 2: Compute the path
LETS_PROJECT_ROOT=$(git rev-parse --show-toplevel)
KIND="{kind}"; EXT="{ext}"; TASK_ID="{task-id or empty}"
case "$KIND" in
plan) DIR=plans ;;
review-*) DIR=reviews ;;
snapshot*) DIR=sessions ;;
*) echo "artifact-path: unknown kind '$KIND'"; exit 1 ;;
esac
mkdir -p "$LETS_PROJECT_ROOT/.lets/$DIR"
STAMP=$(date +%Y-%m-%d-%H%M)
if [ -n "$TASK_ID" ]; then
ID="$TASK_ID"
else
HEX=$(printf '%s' "${CLAUDE_CODE_SESSION_ID:-$$}" | cut -c1-6) # session-id prefix; PID outside Claude Code
ID="$(git branch --show-current | tr '/' '-')-${HEX}"
fi
BASE="$LETS_PROJECT_ROOT/.lets/$DIR/${STAMP}-${ID}-${KIND}"
ARTIFACT_FILE="${BASE}.${EXT}"; N=2
while [ -e "$ARTIFACT_FILE" ]; do ARTIFACT_FILE="${BASE}-v${N}.${EXT}"; N=$((N+1)); done
echo "ARTIFACT_FILE=$ARTIFACT_FILE"
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 · 64 lines · 53 tokens per session scan A 6ae3d887e287
artifact-path is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 871 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…