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 skills add napalmpapalam/skills --skill gogit clone --depth 1 https://github.com/napalmpapalam/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/napalmpapalam/skills/go)<a href="https://agentmods.dev/skills/napalmpapalam/skills/go"><img src="https://agentmods.dev/badge/skills/napalmpapalam/skills/go/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/napalmpapalam/skills/go"><img src="https://agentmods.dev/badge/skills/napalmpapalam/skills/go.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00111 | $0.03072 |
| Opus 5 | $0.00056 | $0.01536 |
| Sonnet 5 | $0.00022 | $0.00614 |
| Haiku 4.5 | $0.00011 | $0.00307 |
Grade A, and why
go 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 9d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go
Plan and ship a feature as vertical slices driven by one living doc — one slice ("a go") at a time. This encodes a fixed method so it never has to be re-explained per feature.
The method is depth-first and just-in-time: build one complete, working layer at a time, fold what you learned back into the doc, then the user clears the chat and starts the next slice from that doc.
Principles (non-negotiable)
- Every slice compiles and runs. A slice is a complete thin path through all the layers it touches — never a horizontal spec fragment. After each slice the project is green: it builds, runs, and the new behavior works.
- A slice is one reviewable PR. Target ≤1000 lines changed, hard cap 1500, lock files excluded. A big feature is several slices, each mergeable on its own, so cross-review stays sane.
- No dead code. Build only what this slice needs. No config, interface, or scaffold for a future slice that hasn't arrived. If it isn't used now, it isn't in scope.
- One slice per session. Planning and building are separate sessions too — a new doc is handed over, not built on (Step 2.5). After a slice lands, the user runs
/clearand starts the next one fresh from the doc. Don't try to do two slices in one go. - What before how. The user often knows the end state, not the path. Settle how the slice will work before writing code (see Step 1).
- Slices are scaffolding, not vocabulary. "Slice", "go", slice numbers, and the doc itself are your planning frame — they mean nothing to anyone reading the repo. Never let them leak into commit messages, PR titles or descriptions, source comments, doc comments, READMEs, identifiers, or test names. Describe the change by what it does, not by where it sat in the plan.
- ❌
feat: slice 2 — transcript loading· ✅feat(transcript): load a session JSONL into scrollable lines - ❌
/// Reading measure, in columns. Configurable in slice 4.· ✅/// Reading measure, in columns.— a not-yet-built option is not a fact about the code; if the constraint is real, say it without the slice number. - ❌ a PR description opening "This is the second go on the quotr doc." · ✅ open with what the PR changes and why.
- ❌
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.
- 9d ago First seen · 143 lines · 111 tokens per session scan A 2f234af0125e
go is a skill published in the GitHub repository napalmpapalam/skills (4 stars, last pushed 7d ago), licensed MIT. It adds 111 tokens to every session and 3,072 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.