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/leonhoffmann86/team-sprint/claude-mdgit clone --depth 1 https://github.com/leonhoffmann86/team-sprintWrote 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/leonhoffmann86/team-sprint/claude-md)<a href="https://agentmods.dev/instructions/leonhoffmann86/team-sprint/claude-md"><img src="https://agentmods.dev/badge/instructions/leonhoffmann86/team-sprint/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 | $0.05352 | $0.05352 |
| Opus 5 | $0.02676 | $0.02676 |
| Sonnet 5 | $0.01070 | $0.01070 |
| Haiku 4.5 | $0.00535 | $0.00535 |
Grade C, and why
team-sprint 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
(`git push`/`git reset --hard`/`git rebase`/`rm -rf`/`Task`/`Agent` — deny is evaluated first Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
lines — `curl` only when a cross-vendor model is configured (`sprint_any_xvendor`; it powers the How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
This is the source of the sprint Claude Code plugin — not an application. There is no
build, lint, or test toolchain. The "code" is:
- three skills (
skills/ticket,skills/bootstrap,skills/update) — markdown prompt files with frontmatter; the skills register the namespaced/sprint:*slash commands themselves — there is deliberately nocommands/directory (wrappers there registered the same names and shadowed the skills; removed in v0.3.3 —skills/is canonical, don't add wrappers back), - a set of bash templates (
templates/) thatbootstrapcopies into a target repo, - the subagent team (
agents/*.md) — six role definitions (planner, navigator, implementer, reviewer-correctness, reviewer-conventions, reviewer-visual) used by the implement loop, - plugin metadata (
.claude-plugin/plugin.jsonand.claude-plugin/marketplace.json— the CLI resolves exactly that marketplace path, keep it there — plusCHANGELOG.md; keep the version in sync across all three when releasing), docs/DISTRIBUTION.md— the binding distribution & separation model: GitHub is the only install channel, also for maintainers (--plugin-diris test-only, e.g. the smoke test); data flows one-way plugin → consumer; updates are pull-based (/sprint:updaterun inside the consumer repo); the registry (~/.config/sprint/registry) is opt-in —bootstrapasks before registering,updateis consume-only and never self-registers; never reach into consumer repos from plugin-dev sessions, and the reverse holds too: sessions running in a consumer repo never write into this plugin repo — fix the vendored copy locally and report the finding for a reviewed plugin-side release,docs/CROSS-VENDOR.md— setup guide for running individual roles on non-Claude models (theopenrouter:prefix + translating proxy, see the configuration section below).
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 · 271 lines · 5,352 tokens per session scan C 5400aa3bfa2b
team-sprint CLAUDE.md is an instructions file published in the GitHub repository leonhoffmann86/team-sprint (1 stars, last pushed 2mo ago), licensed MIT. It adds 5,352 tokens to every session, about $0.0268 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
product-pipeline-public CLAUDE.md
Instructions for lenar-amirov/product-pipeline-public, covering product discovery — pm copilot, 🛑 stop — read this before responding to any user message, tracker integration, quick setup and first launch — value first, setup later.
sideboard CLAUDE.md
Instructions for mmyslin/sideboard: Sideboard's own roadmap lives in GitHub Issues (mmyslin/sideboard). The project is GitHub-only — there is no roadmap.json / local-file mode.
festival GEMINI.md
Gemini CLI instructions for Obedience-Corp/festival: Festival is a goal-oriented project management methodology for human and AI development workflows, driven by the fest and camp CLIs, installed and kept in sync by a third tool, festival. The skills imported below describe how to plan and execute festivals. Load them…
octowiz CLAUDE.md
Instructions for raelli/octowiz, covering octowiz, releasing & deploying, commands, agent skills and issue tracker.
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.