Borrowing it
Nothing to install: this file belongs to gridaco/nothing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gridaco/nothing/main/.agents/skills/oss-standards/SKILL.mdgit clone --depth 1 https://github.com/gridaco/nothingWrote 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/gridaco/nothing/oss-standards)<a href="https://agentmods.dev/skills/gridaco/nothing/oss-standards"><img src="https://agentmods.dev/badge/skills/gridaco/nothing/oss-standards/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/gridaco/nothing/oss-standards"><img src="https://agentmods.dev/badge/skills/gridaco/nothing/oss-standards.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 | $0.00072 | $0.01713 |
| Opus 5.5 | $0.00029 | $0.00685 |
| Sonnet 5.5 | $0.00014 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
oss-standards 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 2mo 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.
This is a copy
88% identical to oss-standards — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
oss-standards
Grida is open source. CI checks catch the mechanical failures — format, lint, typecheck, tests, typos, generated-file freshness. This skill is the extra bar a reviewer enforces because the repo is public, the threat model is public, and the audience for every artifact in a PR includes a stranger who arrived via Google.
The defaults that flip:
- Public-by-default. Names, comments, fixtures, screenshots, commit messages — assume a stranger reads them first. There is no internal channel; everything is the channel.
- Push = publish. A secret in a branch push is a published secret, even if you delete the commit five minutes later. "I'll redact before merge" is not a plan; rotation is.
- Incomplete is worse than absent. "I'll finish it next PR" lands
on
main, gets indexed, and becomes the example the next contributor copies. Usedraft: true, defer the PR, or just don't ship — but don't ship half.
Code
Beyond what CI catches and what CLAUDE.md / naming / code-ts /
code-react already enforce:
- No personal TODOs.
// TODO(me): …, "fix later", "@username knows" — private notes published. Either resolve, or rewrite as a neutral TODO with a tracking issue link. - No machine-specific paths. See the
linkspre-commit gate — absolute paths,~/scratch/...,/tmp/..., and untracked references resolve to nothing for anyone else. - One concern per PR. A reviewer in public cannot accept half a PR; bundled unrelated changes are unreviewable. Split or rebase.
- New public surface is a semver commitment. YAGNI applies everywhere, but in OSS the cost of adding an exported name today is the deprecation path you owe tomorrow. Wait for the second caller.
For bug fixes specifically, the etiology
skill is mandatory — bandaids in main become tribal knowledge that
external contributors have no access to.
Security
The full boundary discipline lives in the
security skill — GRIDA-SEC-<id> tags, the
mandatory review before commit. Two extra OSS gates on top, both
because push = publish:
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.
- 2mo ago First seen · 158 lines · 72 tokens per session scan A 0279a9b7cea6
oss-standards is a skill published in the GitHub repository gridaco/nothing (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,713 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to oss-standards, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.
pr-walkthrough
Create a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough video.
shepherd-pr
Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or…
pr
Create or update a pull request for the current branch in the tldraw repository. Use when the user invokes pr, asks to create a PR, update an existing PR, push current branch changes for review, or prepare a pull request.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
review
Diff-scoped correctness review that reads the codebase around the change — callers, contracts, and invariants — and returns line-anchored findings ranked by severity with confidence, then a merge-risk verdict. Use for reviewing a PR, diff, or named change set. Not for style review, approvals-as-rubber-stamp, or…