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/beppetemp/cartographer/implement-plannpx skills add BeppeTemp/cartographer --skill implement-plangit clone --depth 1 https://github.com/BeppeTemp/cartographerWhat 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 | $0.00107 | $0.01500 |
| Opus 5 | $0.00053 | $0.00750 |
| Sonnet 5 | $0.00021 | $0.00300 |
| Haiku 4.5 | $0.00011 | $0.00150 |
Grade A, and why
implement-plan 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement-plan — plan issues → merged PRs
Source of truth is CONTRIBUTING.md §Plan issues + §Pull requests,
CLAUDE.md (workflow and delegation rules), and docs/index.md §Maintenance
rules. The plan skill covers writing/consuming a single plan. This skill
adds only the multi-plan orchestration and the PR/merge cycle — read
those first; do not duplicate them here.
Preconditions
- Never push in working hours (Mon–Fri 09–18): no
git push/gh pr create/gh pr mergetowardgithub.com/BeppeTemp/cartographerin that window — implement locally, ship outside it. Checkdatefirst. mainis protected: every plan lands via its own PR, squash-merge, CItestgreen. No direct pushes.- Merging a self-authored PR and
git push --force-with-leaserequire explicit user authorization or a standing approval. Never work around the approval gate — surface it and let the user choose.
1 — Wave planning (coordinator)
- Collect the target issues:
gh issue list --label plan(or the subset the user named). Each title already carries its reservedD<n>. gh issue view <n>each; extract the execution order line (plans state it explicitly) and the file-set each touches.- Build the graph, two edge types:
- Hard code dependency — a plan uses code a sibling introduces (e.g. a new client method, a new helper). These form strictly sequential chains: never start a plan before its predecessor is on
main. - Shared file — plans touching the same code, current-state page or
decision topic can conflict at merge. A D entry only touches its owning
docs/decisions/<topic>.md; unrelated topics are not a shared file.
- Hard code dependency — a plan uses code a sibling introduces (e.g. a new client method, a new helper). These form strictly sequential chains: never start a plan before its predecessor is on
- Emit waves: independent roots with disjoint code file-sets run in parallel; dependency chains run internally sequential but in parallel with each other when their file-sets are disjoint. One plan = one PR.
- State the wave plan to the user before spawning (spawning N dev agents + opening N public PRs is outward-facing).
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 · 96 lines · 107 tokens per session scan A 499beb1c9f17
implement-plan is a skill published in the GitHub repository BeppeTemp/cartographer (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,500 once invoked, about $0.0005 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
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…
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…
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.
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…
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.
Cursor rules for Go development with backend scalability
Skill "Cursor rules for Go development with backend scalability" from AmariahAK/atlarix-skills, covering cursor rules for go development with backend scalability, when to use this skill and source.