Borrowing it
Nothing to install: this file belongs to Aniket-a14/SRA. 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/Aniket-a14/SRA/main/CLAUDE.mdgit clone --depth 1 https://github.com/Aniket-a14/SRAWrote 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/aniket-a14/sra/claude-md)<a href="https://agentmods.dev/instructions/aniket-a14/sra/claude-md"><img src="https://agentmods.dev/badge/instructions/aniket-a14/sra/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/aniket-a14/sra/claude-md"><img src="https://agentmods.dev/badge/instructions/aniket-a14/sra/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 | $0.09396 | $0.09396 |
| Opus 5.5 | $0.03758 | $0.03758 |
| Sonnet 5.5 | $0.01879 | $0.01879 |
| Haiku 4.5 | $0.00940 | $0.00940 |
Grade C, and why
SRA CLAUDE.md scanned grade C with 1 finding 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 1mo 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.
- Never run `rm -rf`, `git reset --hard`, `git push --force`, `DROP TABLE`, `kubectl delete`, or similar destructive ops without explicit confirmation. One carve-out, defined in "Branching": `git push --force-with-lease How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
How to work (high-level mindset)
This section is non-negotiable and must never be removed.
The marginal cost of completeness is near zero with AI. Do the whole thing. Do it right. Do it with tests. Do it with documentation. Do it so well that Aniket is genuinely impressed — not politely satisfied, actually impressed. Never offer to "table this for later" when the permanent solve is within reach. Never leave a dangling thread when tying it off takes five more minutes. Never present a workaround when the real fix exists. The standard isn't "good enough" — it's "holy shit, that's done."
Search before building. Test before shipping. Ship the complete thing. When Aniket asks for something, the answer is the finished product, not a plan to build it.
Time is not an excuse. Fatigue is not an excuse. Complexity is not an excuse. Boil the ocean. This is how we think about shipping.
You can outsource the typing. You cannot outsource the understanding. Before you call anything DONE you must be able to explain why the code is correct and exactly where it would break. Tests passing is not understanding. If you can't walk the failure modes out loud, you're not done, you're guessing.
Task sizing — triage before spending tokens
This section is non-negotiable and must never be removed. It gates the tests rule, the fan-out rule, and the self-rating rule. "Do the whole thing" means the whole thing the task actually needs. A full-protocol run on a typo is not thoroughness, it is waste.
Every task starts with a printed triage block, before any work. One exception, and only one: the setup block in "Branching" runs first, because the triage block reports the branch it creates. Four lines:
Size: small | medium | large — why
Tests: local (which ones) | full suite — why
Agents: solo | fan-out (how many, on what) — why
Branch: <branch name> in <worktree path> — see "Branching"
This block is mandatory and verbose on purpose. Aniket reads it to see what mode was picked and to tune these rules over time. A wrong mode is only correctable if the choice is visible. Never skip it, never bury it mid-report. The Branch line is there so that with several sessions running at once, Aniket can tell at a glance which one is about to touch what.
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.
- 1mo ago Changed · +298 lines · +7,494 tokens per session scan A → C 16e0e0098d33
- 1mo ago First seen · 110 lines · 1,902 tokens per session scan A 5e1a2424b4e5
SRA CLAUDE.md is an instructions file published in the GitHub repository Aniket-a14/SRA (24 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 9,396 tokens to every session, about $0.0376 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).