Borrowing it
Nothing to install: this file belongs to dynos-fit/dynos-work. 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/dynos-fit/dynos-work/main/CLAUDE.mdgit clone --depth 1 https://github.com/dynos-fit/dynos-workWrote 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/instructions/dynos-fit/dynos-work/claude-md)<a href="https://agentmods.dev/instructions/dynos-fit/dynos-work/claude-md"><img src="https://agentmods.dev/badge/instructions/dynos-fit/dynos-work/claude-md.svg" alt="Measured on agentmods" 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 | $0.00487 | $0.00487 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
dynos-work 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 6d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code and other Claude-based agents working in this repository.
Release Hygiene
Every PR that changes dynos-work ships as exactly one release. The version number is computed by CI — do not edit it by hand.
What CI does
.github/workflows/release-hygiene.yml runs on every PR open, synchronize, reopen, and label change. It calls scripts/bump_version.py, which:
- reads the current version from the PR's base ref (not from your branch),
- applies one bump —
patchby default, ormajor/minor/noneif the PR carries arelease:major/release:minor/release:nonelabel, - writes the result to all four manifests (
package.json,.claude-plugin/plugin.json,.claude-plugin/marketplace.json,.codex-plugin/plugin.json), - adds a stub
CHANGELOG.mdsection only if no entry for that version exists, - and pushes a
chore: update release metadatacommit to your branch.
It is idempotent: re-running produces the same version, so a PR gets one version no matter how many commits it contains.
What you do
- Write the
CHANGELOG.mdentry. CI's stub is a fallback, not a substitute — it only records the PR title. Describe the behavior change, fix, or maintenance work concretely. - Leave the four manifest version fields alone. Hand-editing them is overwritten by CI, and the bot's push to your branch will reject your next
git pushuntil you rebase. - One entry per PR, not per change. If a PR bundles several logical changes, they still ship under one version. Writing an entry per change produces orphan entries for versions no manifest ever carried.
If you need to know the version your PR will land as, it is the base branch's version plus one patch (or whatever your release:* label selects). scripts/bump_version.py has no dry-run mode — it writes the manifests in place — so read the number off git show origin/main:package.json rather than running the script to find out.
Do not open or prepare a PR with code changes while leaving CHANGELOG.md unchanged.
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.
- 6d ago First seen · 30 lines · 487 tokens per session scan A 57cf34a612c6
dynos-work CLAUDE.md is an instructions file published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 1mo ago), licensed MIT. It adds 487 tokens to every session, about $0.0024 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 instructions, from other repositories
plan-forge version.instructions.md
Version management — Semantic versioning, auto-increment, commit-driven version bumps, release tagging.
plan-forge api-patterns.instructions.md
API patterns for .NET — REST conventions, ProblemDetails, pagination, versioning, error responses.
plan-forge policy.instructions.md
Azure Policy and Initiative compliance — definitions, assignment, compliance state, exemptions, remediation tasks.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.