Step 14 of v4.1 — local-development observability stack with version-pinned container images: - prom/prometheus:v3.0.1 - prom/node-exporter:v1.10.2 (textfile collector enabled) - grafana/grafana:11.4.0 - otel/opentelemetry-collector-contrib:0.115.0 Two complementary export paths from voyage hooks/scripts/otel-export.mjs: - VOYAGE_EXPORT_MODE=textfile → node-exporter textfile collector - VOYAGE_EXPORT_MODE=otlp → otel-collector OTLP/HTTP receiver (:4318) Both feed Prometheus → Grafana. Files: examples/observability/docker-compose.yml examples/observability/otel-collector-config.yaml examples/observability/prometheus.yml examples/observability/grafana-datasource.yml examples/observability/README.md Verified manifest expected_paths (5 files). docker compose config validation runs in Step 16 with proper skip-pattern when docker is unavailable. |
||
|---|---|---|
| .. | ||
| 01-add-verbose-flag | ||
| 02-real-cli | ||
| observability | ||
| README.md | ||
Examples
Complete kalibrerte walk-throughs of the trekplan pipeline for realistic tasks. Each example shows the four artifacts a project directory contains after a full run:
brief.md— task brief from/trekbriefresearch/*.md— research briefs from/trekresearchplan.md— implementation plan from/trekplanprogress.json— execution log from/trekexecute
These are hand-calibrated, not LLM-generated. The point is to give a fork-er a deterministic reference — what the artifacts look like when everything goes right, with a small but real task.
Running pipeline yourself
For your own work, point the four commands at a real project directory:
mkdir -p .claude/projects/2026-05-01-my-task
/trekbrief
/trekresearch --project .claude/projects/2026-05-01-my-task
/trekplan --project .claude/projects/2026-05-01-my-task
/trekexecute --project .claude/projects/2026-05-01-my-task
The artifacts in each example mirror that flow.
Examples
01-add-verbose-flag
Task: add a --verbose flag to a small CLI parser. Touches one
parser file and six command handlers; adds two tests.
Why this example: small enough to read end-to-end in 10 minutes,
but exercises every artifact (research with brief-anchoring, plan with
manifests, progress.json with multi-step git history). Demonstrates
how plan_version: 1.7 schema looks in real life — including the
manifest YAML block per step and the must_contain list-of-dicts
form.
What to study first:
brief.md— note the explicitOut of scopesection and concreteSuccess Criteria(no "make it work" hand-waving).plan.mdStep 1 — note that the FIRST step captures golden output before any behavior change. This is the stability harness pattern.plan.mdStep 5 — note that this step touches 5 files in one commit, and the plan justifies the deviation from the 1–2 file guideline. Plan-critic should accept that justification.progress.json— every step has bothcommit_shaandverify_passed. Resumes work from the last completed step.
Regeneration
Each example has a REGENERATED.md documenting the version it was
calibrated against. When the artifact format changes, the example
needs to be re-built. See the REGENERATED.md file in each example
for triggers and procedure.
Adding a new example
If you have a small, realistic task (touches 1-3 files, has a clear success criterion, finishes in under 30 minutes) and want to add it as an example:
- Create
examples/NN-slug-here/with the same four artifacts. - Add a
REGENERATED.mddocumenting the calibration date and version. - Add a section to this README under
## Examples. - Open an issue on the marketplace describing what the example teaches that 01 doesn't already teach.