Borrowing it
Nothing to install: this file belongs to JackyJiang08/daily-job-match-alert. 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/JackyJiang08/daily-job-match-alert/main/CLAUDE.mdgit clone --depth 1 https://github.com/JackyJiang08/daily-job-match-alertWrote 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/jackyjiang08/daily-job-match-alert/claude-md)<a href="https://agentmods.dev/instructions/jackyjiang08/daily-job-match-alert/claude-md"><img src="https://agentmods.dev/badge/instructions/jackyjiang08/daily-job-match-alert/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/jackyjiang08/daily-job-match-alert/claude-md"><img src="https://agentmods.dev/badge/instructions/jackyjiang08/daily-job-match-alert/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 | $0.12445 | $0.12445 |
| Opus 5.5 | $0.04978 | $0.04978 |
| Sonnet 5.5 | $0.02489 | $0.02489 |
| Haiku 4.5 | $0.01244 | $0.01244 |
Grade A, and why
daily-job-match-alert 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 2d 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 — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Job Match Alert — Project Context
Nightly unattended job-discovery pipeline (Node 20+, ESM, zero-framework). Runs 20:00 America/Chicago via launchd. Collects new Data / AI-ML internship, new-grad, entry-level postings from public sources (SimplifyJobs GitHub lists, public ATS endpoints incl. Workday CXS); scores each JD against N configurable private resume tracks with the Claude Code subscription CLI; writes one dated folder per application date to the Desktop: an HTML shortlist, an XLSX workbook, and warnings.txt only when warnings exist. Same-day reruns merge into that date's report (never shrink). Email-alert collectors exist but are disabled; do not expand them unless a task says so.
Hard constraints
- Subscription-only LLM use via local subscription CLIs (
claudewith a claude.ai login,codexwith a ChatGPT login), both allow-listed. Never add API clients; never use an API key or gateway; ANTHROPIC_/AWS_/OPENAI_ env vars are scrubbed before every CLI subprocess (src/engines/shared.mjs). - No auto-apply, no screening answers, no authenticated scraping.
- config.json, resumes/, intake/, state/, reports are gitignored: never commit personal data (incl. phone/email/resume text) or weaken .gitignore.
- The nightly run must ALWAYS leave a report; failures degrade to warnings (src/warnings.mjs) or, for missing preconditions, an ERROR-{date}.html.
- Dedup keys: original AND final URL hashes (src/state.mjs). Keep gh_jid.
- Deterministic eligibility (US location, May 2027 window) applies in all modes, including local fallback.
Working agreement
- Every behavioral change ships with node --test tests using injected fakes.
- Verify with npm test && npm run demo && npm run chaos. Never run
npm run run(owner's quota + real Desktop); the owner does acceptance. - No new dependencies unless the task allows; no framework/TypeScript migration; do not rename user-facing files or folders.
- package.json overrides (2026-11-03, npm audit 0): exceljs 4.4.0 pins archiver 5, whose glob 7 / minimatch 3–5 chain carries GHSA-g3hv-75wg-m249 (fixed only in minimatch 11.0.1). Overriding minimatch alone breaks glob 7 (glob.sync throws), so the chain is lifted together: archiver ^7 (CJS, same API), glob ^14, minimatch ^11, unzipper ^0.12 (drops fstream/rimraf/glob 7). xlsx parts were byte-identical to the old build apart from docProps timestamps. exceljs's stream.xlsx.WorkbookReader fails on our files under the old deps too (unused here; verify uses xlsx.readFile).
- Report UI lives in src/report-components.mjs + src/report-theme.mjs and is meant to be reused by a future local hub.
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.
- 2d ago Changed · +22 lines · +592 tokens per session b38195ebf655
- 3d ago Changed · +16 lines · +458 tokens per session 7fe8d98d72e2
- 8d ago Changed · +34 lines · +1,039 tokens per session 8182022df31a
- 14d ago Changed · +29 lines · +856 tokens per session 9d3b0c6b0316
- 17d ago Changed · +41 lines · +1,031 tokens per session 5c9ab04be560
- 20d ago Changed · +16 lines · +382 tokens per session 4b256e85570c
- 25d ago Changed · +10 lines · +266 tokens per session 3649e556fcf3
- 26d ago Changed · +31 lines · +835 tokens per session 0a253c487596
- 29d ago Changed · +36 lines · +693 tokens per session 1e1ece2365af
- 1mo ago First seen · 351 lines · 6,293 tokens per session scan A 427a6e31d984
daily-job-match-alert CLAUDE.md is an instructions file published in the GitHub repository JackyJiang08/daily-job-match-alert (2 stars, last pushed 2d ago), licensed MIT. It adds 12,445 tokens to every session, about $0.0498 per session on Opus 5.5. 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 2026-09-13.
daily-job-match-alert CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| daily-job-match-alert CLAUDE.mdJackyJiang08/daily-job-match-alert | Instructions file | 2 | 2d ago | MIT | A | 12,445 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |