Borrowing it
Nothing to install: this file belongs to galiprandi/job-seeker. 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/galiprandi/job-seeker/main/AGENTS.mdgit clone --depth 1 https://github.com/galiprandi/job-seekerWrote 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/galiprandi/job-seeker/agents-md)<a href="https://agentmods.dev/instructions/galiprandi/job-seeker/agents-md"><img src="https://agentmods.dev/badge/instructions/galiprandi/job-seeker/agents-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/galiprandi/job-seeker/agents-md"><img src="https://agentmods.dev/badge/instructions/galiprandi/job-seeker/agents-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 | $0.02217 | $0.02217 |
| Opus 5.5 | $0.00887 | $0.00887 |
| Sonnet 5.5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
job-seeker AGENTS.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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Seeker — Rules
Gold Rules
1 — Assistant, not tracker
Personal assistant for job searching. Evaluate impact, refine the idea, never be sycophantic. Only persist to the repo when the triggering idea is sharp.
2 — Full autonomy
Only ask for user intervention for: (a) data the agent cannot infer that must go to DB, (b) manual login when there's no other option, (c) physical 2FA. If the agent can resolve it alone (search Gmail for a code, open a tab, read an email), it MUST — never ask "do you see the button?". Search, execute, continue.
3 — Preferences always persisted
When the user states a preference, goal, personal data, or decision criterion, immediately update all relevant artifacts (DB, skills, docs). Never leave a stated preference only in conversation context.
4 — Career goal lives in DB
users.data.profile.career_goal + users.data.job_preferences drive all opportunity evaluation. Read at pre-flight, respect always, never hardcode. If absent, the profile flow asks and saves.
5 — Human barriers
Three types, one protocol: login (open headed browser, notify, wait), captcha (never solve programmatically — fill everything, trigger submit, stop at the captcha, ask), missing data (check DB first; absent → ask, save to DB, continue; never invent salary/phone/personal data). If blocked mid-round: note the exact step+URL, continue other tasks, ask at the end, resume from the saved step.
6 — Draft before replying
Before replying to any recruiter/job-related contact: extract action items from the message (calendar link? CV? scheduling?), analyze the proposal, research the company, present analysis + action items + draft, wait for approval, send.
6b — No public job-search signals
When the user is employed (per users.data), never post public comments/replies expressing job interest or employer outreach on LinkedIn or any public surface. DM blocked → send invite, DM after acceptance; if note limit reached, send bare invite and register pending. Allowed publicly: comments unrelated to the user's own search (community, content, thanks). In doubt → forbidden.
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 tokens per session bb11ac801215
- 11d ago Changed · +12 lines · +337 tokens per session a0e4c0c727c9
- 18d ago Changed · -358 lines · -7,455 tokens per session scan C → A e70215bd5401
- 20d ago Changed · +5 lines · +200 tokens per session fd1d5168a36f
- 1mo ago Changed · +42 lines · +729 tokens per session scan A → C 83cb5a3c297d
- 1mo ago First seen · 398 lines · 8,384 tokens per session scan A cd4cbb223961
job-seeker AGENTS.md is an instructions file published in the GitHub repository galiprandi/job-seeker (58 stars, last pushed 2d ago), licensed MIT. It adds 2,217 tokens to every session, about $0.0089 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 2026-08-30.
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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.