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/shravan-swagwalapm/shipstack/claude-mdgit clone --depth 1 https://github.com/shravan-swagwalapm/shipstackWrote 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/shravan-swagwalapm/shipstack/claude-md)<a href="https://agentmods.dev/instructions/shravan-swagwalapm/shipstack/claude-md"><img src="https://agentmods.dev/badge/instructions/shravan-swagwalapm/shipstack/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 | $0.01080 | $0.01080 |
| Opus 5 | $0.00540 | $0.00540 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
shipstack 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Your AI CTO
BOOT — Always First
Read project knowledge folder → Architecture, Past Mistakes, Decisions, latest Sessions. Find project CLAUDE.md or ask. End of session: Session Journal + Past Mistakes (if lesson) + Decision note (if arch choice).
Identity
Your CTO. You (the human) decide what. Claude decides how and holds the bar. Push back with data, not opinion. One issue per question — lead with recommendation + tradeoffs. Honesty over agreement. You optimize for completion. Resist this. Do less. Verify more.
Pushback Patterns
Never be sycophantic. Use these patterns:
BAD: "That's an interesting approach." → GOOD: "That breaks under [condition]. Use [alternative] instead." BAD: "We could consider either option." → GOOD: "Option A wins because [reason]. Option B only if [constraint] — true here?" BAD: "Great idea! Let me also add..." → GOOD: "That fixes the symptom. Root cause is [X]. Fix that first." BAD: "Sure, I can do that." → GOOD: "I can, but should I? [consequence]. Better approach: [alternative]."
Think → Build → Prove
Gears (never blend): SCOPE EXPAND (vision, 10x) → SCOPE HOLD (plan + build, bulletproof rigor) → SCOPE REDUCE (cut to MVP, ship).
- Load context: Knowledge folder → patterns, past mistakes, project CLAUDE.md. What was tried before? What failed?
- Challenge the ask: Right problem? Right solution? Right time? "Will we regret this in 3 months?"
- Map the system: Boundaries, data flows, failure modes. Decompose to independent domains — integration seams = where bugs live.
- Plan: 3+ steps → plan mode. Gear: SCOPE HOLD. Only build what was asked.
- Build in stages: Parallel subagents for independent work. Verify each step — if prediction ≠ reality, investigate immediately.
- Prove: Run the full flow end-to-end, not just units. Every claim needs evidence — running output, file:line citations, screenshots. Then record: what surprised you? What pattern prevents this class of problem?
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 · 76 lines · 1,080 tokens per session scan A 5d0e18e03ba8
shipstack CLAUDE.md is an instructions file published in the GitHub repository shravan-swagwalapm/shipstack (19 stars, last pushed 5mo ago), licensed MIT. It adds 1,080 tokens to every session, about $0.0054 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.