Borrowing it
Nothing to install: this file belongs to volodchenkov/claude-sdlc-agents. 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/volodchenkov/claude-sdlc-agents/master/CLAUDE.mdgit clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agentsWrote 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/volodchenkov/claude-sdlc-agents/claude-md)<a href="https://agentmods.dev/instructions/volodchenkov/claude-sdlc-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/volodchenkov/claude-sdlc-agents/claude-md/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/instructions/volodchenkov/claude-sdlc-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/volodchenkov/claude-sdlc-agents/claude-md.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 | $0.00946 | $0.00946 |
| Opus 5.5 | $0.00378 | $0.00378 |
| Sonnet 5.5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade C, and why
claude-sdlc-agents CLAUDE.md scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| CodeRabbit CLI install (once) | `curl -fsSL https://cli.coderabbit.ai/install.sh \| sh`, then in a new shell `cr auth login` (`cr auth login --region eu` for EU accounts) | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| CodeRabbit CLI install (once) | `curl -fsSL https://cli.coderabbit.ai/install.sh \| sh`, then in a new shell `cr auth login` (`cr auth login --region eu` for EU accounts) | How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code rules for this repo
Commands
| What | Command |
|---|---|
| Install hooks (fresh clone, once) | uv tool install pre-commit && pre-commit install |
Lint + auto-fix, before git add |
pre-commit run --all-files |
Version-bump check (also runs on git push) |
tools/check_version_bump.sh |
| CodeRabbit locally, before every push to a PR | cr review --agent --base master |
| CodeRabbit CLI install (once) | curl -fsSL https://cli.coderabbit.ai/install.sh | sh, then in a new shell cr auth login (cr auth login --region eu for EU accounts) |
Run cr review before pushing and fix everything it reports in one pass: the PR bot reviews incrementally (only commits it has not seen) and its hourly PR allowance is small (this repo got one per hour), so findings left for it arrive one round at a time. The CLI has a separate allowance. Limits per plan: https://docs.coderabbit.ai/management/plans. On the PR, read the review body too — "Outside diff range" findings are there, not in the threads.
Hooks: whitespace / EOF / JSON / YAML, ruff on tools/*.py only (it would rewrite Python examples inside markdown), shellcheck, agent / skill frontmatter (name + description), and on pre-push the plugin version vs origin/master.
Release / version bump
.claude-plugin/plugin.json carries the published plugin version. Every PR that touches agents/, skills/, template/, or tools/ MUST bump it. A PR that ships the same version as master is broken — the marketplace will refuse to update for users.
- Default to patch bumps (
0.5.6 → 0.5.7). Prompt rewording, bug fixes, contradiction cleanup — all patch, even if commits are labelledfeat:. - Minor bumps only when the surface grows: a new agent file, a new skill directory, a new MCP integration, a new top-level capability. If unsure between patch and minor, ask — don't guess up.
- Major (
1.x.0) — never without explicit user instruction. .claude-plugin/marketplace.jsonversionmoves with it — always equal toplugin.json(the pre-push hook checks both).- Bump goes in the same commit as the content change. One PR = one commit (unless explicitly split).
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.
- 5d ago Changed · +16 lines · +385 tokens per session scan A → C 31e4d2725391
- 8d ago Changed · +2 lines · +85 tokens per session 5228171571ee
- 2mo ago First seen · 29 lines · 476 tokens per session scan A 9b4363fb39bc
claude-sdlc-agents CLAUDE.md is an instructions file published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed today), licensed MIT. It adds 946 tokens to every session, about $0.0038 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
claude-sdlc-agents CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-sdlc-agents CLAUDE.mdvolodchenkov/claude-sdlc-agents | Instructions file | 2 | today | MIT | C | 946 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |