A release procedure for publishing new versions of the Cartographer server and client. It uses GitHub, release-please, build pipelines, Homebrew, container images, and Flux for the rollout.

Use it to release Cartographer versions, build and publish binaries, update the Homebrew package and container image, bump the homelab manifest, verify deployment, and update the local client.

It turns the release process into a defined sequence, from merging the release pull request to updating the homelab and local client. It also includes checks before releasing.

deploy — Skill by BeppeTemp

Install

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.

agentmods

npx agentmods add skills/beppetemp/cartographer/deploy

Any agent

npx skills add BeppeTemp/cartographer --skill deploy

Clone the repo

git clone --depth 1 https://github.com/BeppeTemp/cartographer

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00078	$0.01093
Opus 5	$0.00039	$0.00547
Sonnet 5	$0.00016	$0.00219
Haiku 4.5	$0.00008	$0.00109

Measured 2d ago against content hash 4ee004ee5a0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy 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.

.agents/skills/deploy/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy — release di server e client

Cartographer è open source su github.com/BeppeTemp/cartographer. Il bump semver lo calcola release-please dai conventional commits (feat: ⇒ minor, fix: ⇒ patch, feat!:/BREAKING CHANGE ⇒ major): niente più classificazione manuale né tag a mano. Il bot mantiene una release PR aperta che accumula i commit; mergiarla crea tag + GitHub Release, e il tag innesca release.yml (GoReleaser: 4 binari + sha256sums.txt, cask nel tap BeppeTemp/homebrew-tap, immagine ghcr.io/beppetemp/cartographer). Il batching resta: si rilascia mergiando la release PR, non a ogni commit.

L'homelab non si aggiorna da solo: il bump del manifest è manuale (passo 4).

Procedura

Precondizioni:
- main locale allineato a origin (GitHub), make vet && make test verdi;
- doc aggiornata nella stessa sessione delle modifiche.

Merge della release PR — se non esiste, non c'è nulla di releasable dall'ultima release:

gh pr list -R BeppeTemp/cartographer --author app/github-actions --search "release" --state open
gh pr checks <n> -R BeppeTemp/cartographer        # test deve essere verde
gh pr merge <n> -R BeppeTemp/cartographer --squash

Se il bump calcolato è sbagliato, non taggare a mano: commit vuoto con footer Release-As: X.Y.Z e attendere che il bot aggiorni la PR.

Segui la pipeline (release-please crea tag+release → parte release.yml):
```
gh run list -R BeppeTemp/cartographer --workflow release.yml --limit 1
gh release view -R BeppeTemp/cartographer --json tagName,assets -q '{tag: .tagName, assets: [.assets[].name]}'
```
Attesi: 4 binari + sha256sums.txt; commit "Brew cask update" su BeppeTemp/homebrew-tap; manifest ghcr.io/v2/beppetemp/cartographer/manifests/vX.Y.Z pullabile senza auth.
Bump del manifest homelab (repo ~/Documents/Repos/HomeLab/homelab-manifests): k8s/namespaces/ai-tools/cartographer/deployment.yaml → image: ghcr.io/beppetemp/cartographer:vX.Y.Z; commit + push, poi Flux riconcilia (auto entro l'intervallo; per accelerare serve conferma dell'utente: flux reconcile kustomization ai-tools --with-source -n flux-system).
```
kubectl -n ai-tools rollout status deploy/cartographer --timeout=180s
kubectl -n ai-tools get deploy cartographer -o jsonpath='{.spec.template.spec.containers[0].image}'
```

Aggiorna il client locale (via brew, il cask è nel tap):

brew update && brew upgrade --cask beppetemp/tap/cartographer
cartographer version   # deve stampare vX.Y.Z

Report finale: tag = immagine sul cluster = cartographer version locale. Se uno dei tre non è allineato, dillo esplicitamente e indaga prima di chiudere.

Read the full file on GitHub · 49 lines

Files

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.

agents/openai.yaml 215 B

Changes

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 · 49 lines · 78 tokens per session scan A 4ee004ee5a0c

Subscribe to this mod's changes

deploy is a skill published in the GitHub repository BeppeTemp/cartographer (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,093 once invoked, about $0.0004 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.

DevOps and cloud Git and workflow Memory and context go knowledge-base llm-agents mcp

loop-implement

The single implementation loop. It plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks in order, each loading only its named wiki pages, writing tests first, getting an independent test-quality audit, and judging against done; on failure it reflects and retries…

choiyounggi/dev-loop · 94 tokens

knowledge-flush

Drain queued ★ Insight candidates (harvested from your sessions) into the wiki as a reviewed PR. For each candidate it researches and verifies the best-practice against real sources, checks existing wiki layers for duplicates and links, decides the target layer/category (or justifies a new one), runs wiki-ingest, then…

choiyounggi/dev-loop · 117 tokens

wiki-plan

The fixed planning methodology for a capable model. Make every design decision grounded in a bundled wiki page (recording a decision-to-page map), then decompose the work into ordered, self-contained tasks, each naming the exact wiki pages that govern it. Runs as loop-implement step 2.

choiyounggi/dev-loop · 62 tokens

configure

Set up dev-loop's capability-role tool profile — map knowledge (your domain wiki / MCP), verify (your project's test/build/QA command), explore (code search), tacit (past incidents), and design (Figma/visual spec) to the actual tools this environment has, then write /.claude/dev-loop/tools.json (global) or…

choiyounggi/dev-loop · 124 tokens

fkf-use

Use an fkf base safely: inspect status, retrieve bounded context, resolve URIs, traverse declared relations, collect sources, or serve read-only MCP. Invoke for any read or collection workflow in a base.

fmind/fkf · 46 tokens

fkf-learn

Promote verified fkf task-trace findings into a dated log, approved wiki concepts, or project pages. Invoke before closing a session that made a decision, changed behavior, or found a durable dead end.

fmind/fkf · 47 tokens