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/mtvrkan/senior-dev-kit/claude-mdgit clone --depth 1 https://github.com/mtvrkan/senior-dev-kitWrote 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/mtvrkan/senior-dev-kit/claude-md)<a href="https://agentmods.dev/instructions/mtvrkan/senior-dev-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/mtvrkan/senior-dev-kit/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 | $0.01672 | $0.01672 |
| Opus 5 | $0.00836 | $0.00836 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
senior-dev-kit 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
senior-dev-kit — repo CLAUDE.md
This is a publicly distributed Claude Code config kit (MIT, installable as a plugin — see README.md and CONTRIBUTING.md). Every change ships to strangers: assume no shared context, no ability to ask the maintainer, and a machine that is not this one.
global-CLAUDE.md and presets/*/CLAUDE.md are templates installed into ~/.claude/ or a
project's .claude/ — don't confuse them with this file, which is scoped to editing the kit
itself.
Commands
- Test:
npm test(targeted:node --experimental-strip-types --test scripts/<file>.test.ts) - Validate frontmatter/routing:
npm run validate - Full gate (run before considering any change done):
npm run check— runs test, validate, link-check, consistency-check, docs-check, routing-eval, behavior-eval, check-plugin, check-install, typecheck, lint, markdown-lint, audit —routing-evalandbehavior-evalare the only two steps that measure model behavior rather than file contents, and both score live only under their env flag (RUN_ROUTING_EVAL=1,RUN_BEHAVIOR_EVAL=1; in PowerShell set$env:NAME=1first — there is no inline prefix form) —check-installis the only step that looks outside the repo: it compares~/.claudewith this checkout and fails when the installed copy is behind. Every other step verifies the repo against itself, which is how a green gate once coexisted with a day-old install running the content the work had just replaced. It skips loudly where there is no copy install. - Type-check only:
npm run typecheck| Lint only:npm run lint - Installer dry run:
node scripts/install.mjs --dry-run - Landing page: not on this branch. The page source lives on the
site-srcbranch and the rendered output ongh-pages; a clone of the kit carries neither, because nobody installing a Claude Code configuration kit needs a website.site/is git-ignored here and is the path that branch gets checked out into —git worktree add site site-srcto work on it..github/workflows/site.ymlchecks out both branches, renders, and force-pushes a single orphan commit togh-pages; pushing to either branch publishes. - The split does not weaken the derivation: every number the page states is read from this
branch's contents at build time by
scripts/gen-site.ts(agent/skill/preset counts, deny rules, the always-loaded line budget, the gate's own step list).site-checkand consistency check 28 therefore run in that workflow, not innpm run check— check 28 says so out loud when it scans nothing, rather than passing silently. - The
site-srctemplates andstyle.csskeep their contributor comments even though global-CLAUDE.md's SHIPPED SOURCE IS PUBLIC forbids comments in browser-served files: nothing on that branch is served as-is.gen-site.tsstrips every one at build time (stripTemplateNote/stripPartialNote/stripCssComments), andsite-checkfails the publish if any survives into an artifact. Write the rationale in the source; the visitor never receives it. Do not re-open this as a rule violation.
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.
- 4d ago First seen · 96 lines · 1,672 tokens per session scan A e92f62bb9255
senior-dev-kit CLAUDE.md is an instructions file published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 4d ago), licensed MIT. It adds 1,672 tokens to every session, about $0.0084 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.