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 instructions/oddbit/shrtnr/claude-mdgit clone --depth 1 https://github.com/oddbit/shrtnrWhat 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 | $0.01790 | $0.01790 |
| Opus 5 | $0.00895 | $0.00895 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
shrtnr CLAUDE.md 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Styling
- No inline styles for global design. Use centralized style files imported by components/pages.
Releases
Release tracks (version bump on main drives each):
| Target | Manifest | Tag prefix |
|---|---|---|
| Cloudflare Workers app | root package.json |
app-v* |
| TypeScript/npm SDK | sdk/typescript/package.json |
npm-v* |
| Python/PyPI SDK | sdk/python/pyproject.toml |
py-v* |
| Dart/pub.dev SDK | sdk/dart/pubspec.yaml |
pub-v* |
Use scripts/bump-sdk-version.sh <npm|python|pub> <version> to bump SDK versions. It edits the manifest, adds a placeholder CHANGELOG entry, and refreshes lockfiles. Replace TODO: fill in release notes. before commit.
On "update the version" / "bump version" / "create a release":
- Bump version in the correct manifest per semver. Confirm track if ambiguous.
- Add a concise section (paragraph or bullets, not a commit log) to the matching
CHANGELOG.md(root,sdk/typescript/,sdk/python/,sdk/dart/). - App track only: the OpenAPI spec embeds
info.versionfrom rootpackage.json, so every app version bump stales all three SDK hashes. Before committing, run./scripts/spec-hash.shand updatex-spec-hashinsdk/typescript/package.json,spec_hashinsdk/python/pyproject.toml, and the# x-spec-hash:comment insdk/dart/pubspec.yamlin the same commit. CI'ssdk-spec-driftgate fails otherwise. - Commit. Do not push.
- Dart only: also create the tag locally, do not push:
git tag pub-v<version>. pub.dev publishes on tag push. App/npm/Python tag from CI after publish.
Full details: docs/release-automation.md.
SDKs
- SDK parity. Any change to one SDK under
sdk/must be evaluated and applied to the others (public methods, models, auth, errors, base-URL handling). Single-SDK changes require explicit rationale in the commit message. Default: SDKs move together. - README parity. All SDK READMEs stay in lockstep (install, usage, auth, feature list), adjusted only for language idioms. Removing/renaming a documented feature in one requires the same edit in the others.
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 · 104 lines · 1,790 tokens per session scan A c2863845112b
shrtnr CLAUDE.md is an instructions file published in the GitHub repository oddbit/shrtnr (12 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,790 tokens to every session, about $0.0089 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 instructions, from other repositories
betting-brain-v3 CLAUDE.md
Instructions for brendadeeznuts1111/betting-brain-v3, covering claude.md, 🎯 current project status (2025-10-07), ✅ production ready, recent recovery (last 2 hours) and quick wins available.
MisakaNet AGENTS.md
Instructions for Ikalus1988/MisakaNet, covering misakanet agent 规则, 🛡️ 崩溃保护(强烈推荐), 用 fatal-guard 包装你的进程,崩溃时自动捕获墓碑, 墓碑自动转为 draft lesson and 或通过管道直连.
MisakaNet CLAUDE.md
Instructions for Ikalus1988/MisakaNet, covering misakanet failure memory, quick start, search for a failure, get a specific lesson and submit via mcp (no github needed).
rewind AGENTS.md
Instructions for pdugan20/rewind, covering rewind, work modes, development commands, agent configuration and architecture overview.
svelteflare AGENTS.md
Instructions for pinebasedev/svelteflare, covering agent rules for this project, theme fidelity (non-negotiable), talking to the user and deep-dive skills.
FlareMo AGENTS.md
AGENTS.md instructions for realchendahuang/FlareMo, covering flaremo agent 指南, 项目定位, 常用命令, 修改规则 and issue 和 pr 流程.