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/sayantan94/appliedin/claude-mdgit clone --depth 1 https://github.com/sayantan94/AppliedInWrote 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/sayantan94/appliedin/claude-md)<a href="https://agentmods.dev/instructions/sayantan94/appliedin/claude-md"><img src="https://agentmods.dev/badge/instructions/sayantan94/appliedin/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 5.1 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
AppliedIn 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 6d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Read AGENTS.md before changing anything. It is the guide for working on this repo: layout, how to add a job preference or a per site playbook, how to debug the browser agent, and the invariants that must stay enforced in code.
Everything in this file is a pointer to that one. If the two ever disagree, AGENTS.md is right.
If you are asked to set this repo up and start the server, follow
AGENTS.md → Setup exactly.
It is scripted end to end through a single entry point, ./appliedin. Ask the
human for the three things only they have (an OpenAI key, their résumé at
resume/base.tex, and a company or two to watch) rather than inventing values,
and verify each step before moving to the next.
The rule that outranks the rest
An application is sent under a real person's name and cannot be recalled. A missed application costs an opportunity; a wrong one costs credibility. When a change trades safety for throughput, it is the wrong change.
Before you start
- Restart the daemon after any
src/change. There is no hot reload, and the browser cachesweb/app.jsandweb/styles.css, so a UI change needs a hard reload as well. Testing stale code has wasted more time here than any bug. - Run the tests:
.venv/bin/python -m pytest -q. They are offline by design; never add one that reaches the network or drives a browser. - Diagnose with evidence, not theory. The worst bug in this repo's history was guessed at three times and solved once, by reading the browser session's own report instead of its one line verdict. AGENTS.md has the drill.
Do not
- Move a guard from code into a prompt. The invariants in AGENTS.md hold because the tool layer enforces them regardless of what the model emits.
- Commit
.local/,resume/base.texor anything underoutput/. They hold real personal data.config/watchlist.yamlandconfig/preferences.yamlare tracked, so treat them as public. - Add a preference field to the interface without wiring it into
discovery/relevance.py. A setting nothing reads is a lie.
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.
- 6d ago First seen · 44 lines · 525 tokens per session scan A 87384288e0a5
AppliedIn CLAUDE.md is an instructions file published in the GitHub repository sayantan94/AppliedIn (7 stars, last pushed 2d ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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).
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).
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.
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.
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.